 Your new post is loading...
|
Scooped by
Charles Tiayon
June 16, 2:08 PM
|
New study finds a common neural system builds a language across languages "Bilingualism is Driven by a Single Neurological “Grammar Engine” New study finds a common neural system builds a language across languages NYU researchers have found that bilingualism is not powered by separate grammar engines in the brain, but, rather, by a common neural system that works across languages. Above: A restaurant in Silves, Portugal. Photo credit: Mary Salen/Getty Images It’s not uncommon for bilingual speakers to mistakenly apply the grammatical rules of one language while speaking the other—for example, saying “I have 20 years” instead of “I am 20” when asked about their age. Some may wonder if these language mashups are evidence of deeper neurological distinctions among languages: If you speak English and Spanish, for instance, do you have an English “grammatical engine” that learns and applies English rules and a Spanish one that learns and applies Spanish rules? A new study by a team of New York University scientists finds that, in fact, bilingualism is not powered by separate grammar engines in the brain, but, rather, by a common neural system that works across languages. “Our research suggests that brains have a single grammatical engine that fuels all of the languages we speak—rather than separate engines for each one,” explains Esti Blanco-Elorrieta, an assistant professor of psychology and neural science at NYU and the senior author of the study, which appears in JNeurosci. “We show that the same brain patterns support grammar in English and Spanish, indicating that human language may be built from neural computations that transcend any one language.” While previous research has found neurological commonality across speakers of different languages and other NYU research has explored “bilingual brains,” less clear is how the brain builds grammar across languages in bilingual speakers. To address this, Blanco-Elorrieta and Xuanyi Jessica Chen, an NYU doctoral student and the paper’s first author, used magnetoencephalography (MEG) to track brain activity millisecond-by-millisecond while Spanish-English bilingual speakers transformed both English and Spanish words into grammatically correct forms. For instance, participants would hear a singular form of a word (“boat” [English] or “barco” [Spanish]) and were asked to say the plural version of the term (e.g., “boats” or “barcos”). We show that the same brain patterns support grammar in English and Spanish, indicating that human language may be built from neural computations that transcend any one language. Esti Blanco-Elorrieta Assistant Professor of Psychology The researchers also tested how participants responded to both cognates—words in different languages that share a similar meaning, spelling, and pronunciation because of their common linguistic roots—and “pseudowords” (made-up words such as “paple”). This method, which reached beyond existing words in English and Spanish, was aimed at determining if the same neural mechanisms apply when novel words enter our vocabulary. The findings showed that the brain relies on a shared neural mechanism for grammar across languages, even when words differ in sound or structure. Moreover, the same neural system also applied to completely novel words (i.e., pseudowords), further suggesting that the brain implements grammar as a reusable computation—or universal language template—rather than deploying multiple language-specific rulebooks. “The results provide some of the clearest neural evidence to date that grammatical computations are shared across languages in bilingual speakers,” says Blanco-Elorrieta, who previously teamed up with Chen to create a calculator to measure multilingualism. “More broadly, because the brain appears to use a common neural system across languages, our findings offer new insight into how we communicate and learn new languages.” This research was supported by grants from the National Science Foundation (BCS-Grant 2446452) and the National Institutes of Health (R00 DC019973-01)." Original publication date: Jun 15, 2026 https://www.nyu.edu/about/news-publications/news/2026/june/bilingualism-is-driven-by-a-single-neurological--grammar-engine-.html #metaglossia #metaglossia_mundus
"RWS wins "Machine Translation Solution of Year" award for third year running
Latest AI Breakthrough win underscores RWS's leadership and innovation in enterprise AI translation
MAIDENHEAD, England, June 25, 2026 /PRNewswire/ -- RWS (AIM: RWS.L), a global AI solutions company, has won "Machine Translation Solution of the Year" at the 9th annual AI Breakthrough Awards for Language Weaver Pro – the latest sign of its accelerating momentum in enterprise AI translation.
Language Weaver Pro is RWS's most advanced AI translation solution. Built in partnership with Cohere, the 100+ billion parameter model is purpose-trained for translation and engineered to help enterprises and government organizations translate business-critical content with greater accuracy, fluency and security.
Launched in early 2026, Language Weaver Pro is purpose-built to handle context, ambiguity and complex content – including high-end marketing and creative copy. In both human-led and automated benchmarking, it outperformed competitors across sentence- and paragraph-level datasets spanning technical and marketing content.
"I couldn't be prouder of what the team has achieved with Language Weaver Pro," said Ben Faes, CEO of RWS. "Working with Cohere's scientists and our own linguists, we've created our most advanced translation model yet – and embedded it into a product that enterprises can actually run at scale, without runaway costs or the hallucinations that come with general-purpose AI."
Language Weaver Pro is also integrated across the Trados portfolio, putting advanced AI translation directly into the tools linguists and organizations already use throughout the localization process.
"Translation is one of the original AI applications, and yet it remains one of the few categories where the best consumer-grade output still falls short in the regulated, brand-sensitive environments that most enterprises actually operate in," said Steve Johansson, Managing Director, AI Breakthrough. "RWS has built Language Weaver Pro to operate in exactly those environments, with a large language model purpose-built for translation, embedded linguistic expertise and the deployment flexibility that enterprises require."
Language Weaver Pro sits at the heart of RWS's Language Intelligence capability, combining multilingual AI models, RWS's linguistic expertise and secure language technology – giving organizations the accuracy, adaptability and governance to act on multilingual content in the most complex global environments.
This year's AI Breakthrough Awards attracted the strongest field in their near-decade history, with thousands of nominations from more than 20 countries across categories spanning Agentic AI, Generative AI, Computer Vision, AIOps, Robotics and Natural Language Processing – making RWS's third consecutive win all the more significant.
Learn more about Language Weaver Pro.
About us
RWS is a global AI solutions company empowering the world's most trusted enterprise AI.
Our proprietary Cultural Intelligence Layer, powered by 250,000 data specialists, cultural and language experts and deep domain professionals, backed by 45+ patents, makes enterprise AI culturally fluent, contextually accurate and secure, ensuring every interaction reflects a brand's tone, context and customer values.
Through our Generate, Transform and Protect segments, we deliver intelligent content, enterprise knowledge, large-scale localization and IP protection for global growth. Trusted by 80+ of the world's top 100 brands, RWS provides the confidence, governance and expertise organizations need to deploy AI safely, responsibly and at scale.
Headquartered in the UK, RWS is listed on AIM."
https://www.prnewswire.com/news-releases/rws-wins-machine-translation-solution-of-year-award-for-third-year-running-302810823.html
#metaglossia
#metaglossia_mundus
"The Future of Translation Services in the U.S.: Why ‘Location-Based’ No Longer Means Local
So, if you had to get a document translated for a visa or immigration application, you would search your local area – maybe a notary who did translations on a part-time basis, maybe a bilingual professional in the community. The nearness seemed to be a stand-in for reliability. This conviction has been unshaken, in a way. Not because the quality of local translators has decreased, but because the definitions of ‘accessible’ and ‘trustworthy’ have grown – and geography can no longer keep up. The U.S. translation services market has restructured itself beyond the zip code, and USCIS applicant translations have become a more significant part of the business.
I’ve spent considerable time watching this shift unfold, and what’s most striking isn’t the technology behind it. It’s the change in what people expect. When I look at how immigrants and visa applicants are actually making decisions today, the pattern is clear: they’re not asking “who’s closest?” They’re asking “who’s most reliable, fastest, and most likely to get this right the first time?” In that context, platforms like RapidTranslate.org/locations have gained real traction not by being local to any single city, but by being consistently reachable from every city simultaneously.
How the Old System Worked, and Why It Broke
The traditional translation model wasn’t built on competence. It was built on logistics. Before cloud-based document handling became routine, you genuinely needed someone physically present. Physical stamps, wet signatures, and in-person handoffs made proximity a functional necessity, not a preference. A certified translator in Chicago couldn’t efficiently serve a client in Albuquerque when everything had to move by mail or scheduled appointment.
This created something that looked like a market but functioned more like a lottery. If you lived in a large metro area with a substantial immigrant population, you had real choices. If you lived somewhere smaller, your access to qualified, USCIS-familiar translators might be limited to two or three providers – none of whom necessarily specialized in your specific language pair or document category. The quality of your translated documents ended up depending heavily on where you happened to live, which is a strange basis for something as consequential as a federal immigration application.
What USCIS Requires, and What It Doesn’t
Here’s what often surprises people: USCIS imposes no geographic requirement on translators whatsoever. What it does require is specific. Any foreign-language document submitted with an application must include:
A complete English translation of the entire document.
A signed certification from the translator.
A declaration of competency in both languages.
A statement confirming the translation is accurate to the best of their knowledge.
The agency does not require the translator to hold a license, pass a government exam, or operate from any particular state. Selecting a provider based on physical proximity, when none of these standards reference location at all, means optimizing for something with zero bearing on whether your application advances or lands in a Request for Evidence.
The Completeness Standard Most Applicants Underestimate
The most common reason certified translations get flagged isn’t a meaning-level error. It’s a completeness problem. USCIS requires that every element of the source document appear in the English version: official seals, stamps, headers, margin annotations, everything. A birth certificate that omits a municipal seal or leaves a government heading untranslated will draw scrutiny regardless of how precise the name and date fields are. Missing a single structural element is enough to trigger a delay that can stretch across months.
The Standardization Advantage Local Providers Can’t Easily Match
When a translation service handles thousands of USCIS-bound documents per month, formatting stops being a judgment call and becomes institutional. The certification statement reads consistently, the layout mirrors what federal reviewers are accustomed to seeing, and edge cases: documents with multiple embedded languages, deteriorated stamps, and handwritten notations get resolved through established internal workflows rather than improvised on the spot.
A freelance translator – even a deeply skilled one – builds their process from personal habit. There’s no external compliance system enforcing that their certification statement matches current USCIS formatting expectations or that their layout of a foreign civil registry document aligns with what reviewers at a particular service center have come to expect. That’s not an indictment of individual capability; it’s simply the structural reality of solo work operating without an institutional framework behind it.
Why Consistency Translates Directly to Faster Approvals
Larger platforms that concentrate specifically on certified translation for federal submissions maintain internal style guides mapped directly to USCIS requirements. The practical differences show up clearly:
A client in Miami and a client in Seattle receive identically formatted documents.
Certification statements follow the same structure across every single order.
Non-standard cases are resolved by established protocol, not on-the-spot judgment.
That uniformity carries real weight when the agency processing your application handles millions of filings annually and has limited bandwidth for documents that require a second look. A document that mirrors what reviewers already expect to see moves through the process with considerably less friction.
Speed and Accessibility in 2026
The last argument that genuinely favored local providers was turnaround time. Walk in, hand over the document, and return the next day. That edge has effectively disappeared. Most established online translation services now deliver standard certified documents within 24 to 48 hours, with expedited options when deadlines press harder. The entire workflow – uploading the source material, receiving the certified translation, downloading the finished document – happens without a physical visit or office-hours constraint.
Conclusion
For applicants managing immigration timelines, this is practical, not philosophical. Visa appointment dates don’t flex, application windows close on schedule, and biometrics appointments aren’t forgiving. Having access to certified translation at midnight, from a rural area, without coordinating anyone’s availability, is no longer a differentiating feature. It’s simply what applicants now expect as a baseline.
What the market has absorbed by mid-2026 is that “local” was never the real point. Qualified, consistent, and fast – those were always the criteria that mattered. It just took the industry a while to figure out how to deliver all three without a storefront."
by Staff
June 24th, 2026
https://triad-city-beat.com/the-future-of-translation-services-in-the-u-s-why-location-based-no-longer-means-local/
#metaglossia
#metaglossia_mundus
"The complete translation project of the Talmud was launched at the residence of the President in the presence of President Herzog and businessman and philanthropist Patrick Drahi
In a ceremony at the President's Residence in Jerusalem on Wednesday, Israel marked the completion and publication of the first full French translation of the Babylonian Talmud. The project is based on the landmark commentary of the late Rabbi Adin Even-Israel Steinsaltz and funded by the Patrick and Lina Drahi Foundation.
The date was not chosen by coincidence. The ceremony fell on the 9th of Tammuz, exactly 782 years after the Paris Disputation of 1242, which ended with King Louis IX ordering the burning of thousands of Talmud volumes and Jewish manuscripts in the city's public square. Marking the launch on that same date was a deliberate act of historical closure.
President Isaac Herzog, who hosted the event alongside businessman and philanthropist Patrick Drahi, called the translation "a gateway to making the Talmud accessible to the entire world." The project is expected to open Talmudic study to millions of French speakers across France, Belgium, North Africa, Canada, and Israel's own French-speaking immigrant community.
The translation builds on Rabbi Steinsaltz's pioneering method, developed over nearly five decades and guided by his conviction that "the Torah is the inheritance of every Jew." Steinsaltz restructured the traditional page layout, divided the text into paragraphs, vocalized the Aramaic, and added scientific, historical, and biographical commentary, making the Talmud's dense Amoraic discussions accessible to the modern reader. He passed away in 2020, having received the Israel Prize for his work.
Drahi, whose foundation financed the project, reflected on what the Talmud's culture of debate might offer the wider world: "Dispute is an inseparable part of the Talmud, and in the Talmud it leads to mutual enrichment. I hope this edition will also contribute to our ability to listen to the voice of the other."
Rabbi Meni Even-Israel, the rabbi's son and CEO of the Steinsaltz Center, framed the publication in broader terms: "Today's event marks the continuity and eternity of the Torah of Israel and the people of Israel."
Disclosure: The Drahi family, which leads the Patrick and Lina Drahi Foundation, owns i24NEWS"
i24NEWS
2 min read
June 25, 2026 at 10:27 AM
latest revision June 25, 2026 at 10:26 AM
https://www.i24news.tv/en/news/international/culture/artc-the-first-complete-french-translation-of-the-talmud-is-complete
#metaglossia
#metaglossia_mundus
"Jurisdictions increasingly expect their offices to provide multilingual services in spite of resource constraints.
Artificial intelligence
Diversity and Inclusion
Public Engagement
A new Washington law that went into effect this month calls for state leaders to create standardized language access guidelines in a bid to enhance the government’s service delivery.
The Washington bill, signed into law by Gov. Bob Ferguson in March, directs the state’s Office of Equity to develop guidelines for agencies to ensure the consistent and effective delivery of state-administered content, such as written, verbal, virtual or recorded communications.
A similar effort is underway in California after lawmakers passed a bill late last year that aims to enhance the public’s access to and participation in state and local legislative meetings. Starting July 1, for example, agencies must offer multilingual translation services for public meeting agendas and other communications.
Story Continues Below Sponsor Message
The bills reflect a longstanding priority among state and local leaders across the U.S. to expand language accessibility, including translating real-time events or written content, for increasingly diverse communities. But the cost and difficulty of hiring human interpreters presents major challenges to many jurisdictions hoping to help residents better understand critical announcements, public meetings and other resources.
Artificial intelligence has been touted as a solution to optimize translations for government settings, said Suresh Venkatasubramanian, director of Brown University’s Center for Tech Responsibility. But the technology should not be treated as a blanket solution to language accessibility.
Wisconsin policymakers, for instance, introduced legislation last year that would have allowed state and local organizations to permit the use of AI translation tools instead of human interpreters in courtrooms. The bill, which received pushback from observers concerned that AI interpretations were not suitable for replacing human knowledge and judgement, died earlier this year after it failed to pass both chambers.
But recent survey findings suggest growing confidence in AI-powered translation tools among professionals who manage meetings and events. The data, based on more than 200 respondents, found that nearly 95% of professionals agreed that AI translation solutions are easier and more affordable than human interpreters. At the same time, nearly 80% of respondents said the share of non-English speakers is increasing at events.
The report, commissioned by software company Wordly and conducted by Dimensional Research, also found that 66% prefer AI-powered translations and only 25% said they still prefer human interpreters.
Those findings are particularly valuable for state and local leaders who may have been hesitant to use AI for translation services thus far, said Dave Deasy, chief marketing officer of Wordly.
As more jurisdictions deploy AI tools to translate communication during public meetings, public safety broadcasts and other events, “we have found with a lot of communities, as they have started to offer more language support, they’re actually getting more [community] participation,” Deasy said.
Story Continues Below Sponsor Message
That means more individuals can, for instance, better understand and comply with policy changes to benefit programs they’re enrolled in, developments in immigration enforcement laws or participate in feedback opportunities like public comment periods, Deasy said.
While language accessibility and inclusivity is a vital function of government, AI-based solutions to language gaps should not come at the cost of responsible adoption, testing and implementation of the technology, Venkatasubramanian said.
“Serving a population is not just about the cheapest way to do it, but the most efficacious way to do it,” he said. For instance, the common argument for AI translation tools is their potential to reduce expenses for hiring and retaining human interpreters, which could be tempting for governments already facing limited funding and staff capacity, he explained.
Realistically, state and local leaders should prepare to spend the appropriate money and time to vet AI translation services from vendors and ensure outputs are accurate and relevant to local community needs, Venkatasubramanian said.
He suggested governments and agencies looking to adopt AI translation tools to start with temporary contracts that enable them to pilot such services. This approach can also help government leaders exercise more leverage to customize and evaluate AI tools based on their unique needs, he said.
Jurisdictions often have specific terms for their geographic locations, department titles, documents and other government-affiliated language, and officials must ensure a proposed AI model can address and maintain such specificities across languages, he explained. That is where an AI product that worked for one city may be less effective for another, making it crucial for state and local leaders to conduct their own evaluations of such solutions.
Venkatasubramanian also underscored the value of human interpreters as part of the process of adopting and deploying translation tools. While AI-powered translations are relatively accurate and successful for one-on-one conversations, like between locals and tourists, government-based use cases require heightened scrutiny when a resident’s safety and well-being could be on the line.
Story Continues Below Sponsor Message
Indeed, human interpreters can be especially valuable when it comes to assessing the accuracy and validity of AI-powered translations, as they can better understand nuances and sentimental differences between languages, Minnesota officials said at Code for America’s 2026 Summit last month in Chicago.
During a breakout session at the conference, officials for the Minnesota Department of Human Services also shared a framework to help government leaders assess whether or not AI is the right solution to language translation services.
Venkatasubramanian also pointed to Boston as an example of a municipality taking a “very thoughtful and careful” approach to AI’s use in government, including AI-enabled translations. In 2023, city officials released generative AI guidance that directs municipal staff to limit their reliance on the technology for conducting translations.
For instance, users should keep in mind the limitations of the technology because “it is not well documented the extent to which ChatGPT and other models can use other languages,” according to the guidance. The document also encourages users to avoid using content generated in a language they are not familiar with without consulting someone proficient in the language and to ensure AI models can consider different regional dialects within the same language.
Ultimately, an AI translation tool “is going to be much better for you in the long run, if you have a solid [AI] system that is actually tuned to your context,” Venkatasubramanian explained, adding that “you have to do your own due diligence.”"
By Kaitlyn Levinson | June 25, 2026 03:30 PM ET
https://www.route-fifty.com/digital-government/2026/06/ai-translation-tools-require-due-diligence-state-and-local-leaders-expert-says/414436/?oref=rf-homepage-river
#metaglossia
#metaglossia_mundus
"For centuries, people have dreamed of undoing Babel.
Sci-fi novelists envisioned universal translators, and linguists devised international languages, all in pursuit of a world where one person could speak and another could understand, regardless of where either was born.
Artificial intelligence appears to be taking humanity one step closer toward that goal.
AI-powered tools are already being widely used by lawyers to translate legal documents from one language to the next. The mass market romance publisher Harlequin has turned to AI to translate its novels for international audiences. And hospitals are deploying AI translation to communicate directly with patients in multiple languages.
The speed and skill with which these AI-powered translation tools operate are certainly impressive.
But there is an important frontier for translation technology, one that it might never be able to breach: the poem.
Stay ahead of the curve. Receive expert-led daily news & analysis.
Please enter your email...
Get our newsletter
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
That’s because translating poetry, thus far, has been a uniquely human experience. It demands intimate knowledge of two languages, which large language models certainly possess. But it also requires a mastery of different cultures and perspectives, what literary critic Gayatri Chakravorty Spivak calls a “worlding” of language and culture.
Pushing the limits of language
When scholars have studied the creativity of chatbots by prompting them to produce poetry, they’ve noticed that the poems tend to be more homogeneous and standardized than those written by humans.
Chatbots’ poetry translations have similar issues.
AI seems to struggle in three main areas: rendering metaphor, decoding complex sentence structure and creatively conveying mood or emotion.
To demonstrate these flaws, I worked closely with Adeeba Shahid Talukder, an award-winning poet and translator, to write this piece and to translate the 1953 poem “Mulāqāt,” or “Meeting,” composed by one of the most famous Urdu poets of the 20th century, Faiz Ahmed Faiz.
Pakistani poet Faiz Ahmed Faiz. Wikimedia Commons, CC BY-SA
Faiz was born in 1911 in Sialkot, in pre-Partition India. In 1947, when that area in the Punjab became part of present-day Pakistan, Faiz became a citizen of the newly founded country, though his relationship with it was marked by both hope and disillusionment. He lived in different parts of the world for long stretches of time, but he returned to Pakistan toward the end of his life. He died there in 1984.
His poetry is celebrated for its marriage of classical tropes like the ache of unfulfilled longing for the beloved — and the lover’s willingness to be consumed or destroyed in his pursuit of her — with the political struggles of his time, like the plight of working people and the dream of a Marxist revolution. His poetry is notoriously difficult to translate because of its highly ornate, extended metaphors, which have few easy equivalents in English. This forces the translator – be it human or machine – to push the limits of language.
From 1951 to 1955, Faiz was imprisoned on allegations of sedition against the Pakistani state. His first three months were spent in solitary confinement.
From Faiz’s letters, scholars learned that despite the isolation of his imprisonment, he felt as if the experience made him more attuned to his senses, as if he were “falling in love again for the first time.” His time in jail was also among his most prolific as a poet, with “Meeting” composed during his sentence.
Here’s our translation of the opening verses of “Meeting”:
This night is the dark,
lush tree of a grief greater
than you and I—
greater, for caravans
of torch-bearing stars
have lost themselves
in the siege of its branches;
in its shadow, a thousand moons
have wept away all their light.
This night is the dark,
lush tree of a grief greater
than you and I—
but from the tree of this very night
the amber leaves
of these moments
have fallen,
grown entangled
in your locks and flowered
as the fires of pomegranate
blossoms; its dew
has rained drops of silence
upon your brow,
bedecked it with a silver
string of pearls.
When prompted to provide a “lyrical translation into English,” ChatGPT produced the following:
This night is a tree of pain,
Vaster than you, vaster than me.
Its branches bear
Thousands of torches in place of stars,
Caravans lost
Within a thousand moons’ shadows,
And all my light has wept itself away.
Yet from this very tree,
A few golden leaves of fleeting moments
Fall into your hair,
Entwined, they bloom like roses.
From its dew in quiet,
A few drops rest upon your brow,
And glitter like tiny diamonds.
Chatbots fail at translation’s most basic task
When Faiz composed “Meeting,” he had been separated from his wife and two daughters for two years. He was keenly aware of missing parts of their childhoods that would never return.
This biographical information can help translators understand the poem’s exploration of “vaṣl,” or the meeting of lover and beloved. A common trope in classical Urdu poetry, it usually captures the joy and exultation of the lovers’ union.
But in Faiz’s poem, the union with the beloved also contains an acute awareness of mortality and the transience of beauty – a recognition of what has been lost, and the suffering still to come.
That’s why we rendered the opening lines of “Meeting” as “This night is the dark,/lush tree of a grief greater/than you and I.”
ChatGPT’s translation is more literal: “This night is the tree of pain.”
While there is nothing technically wrong with this translation, the chatbot’s version doesn’t capture the nuances of the tree metaphor and the way its dense, expansive branches can encompass the complexity and beauty of the emotions evoked by the night of the lovers’ union.
AI also fails to grasp the poem’s intricate sentence structure. ChatGPT has translated “in its shadow a thousand moons / have wept away all their light” as a nonsensical construction: “Within a thousand moons’ shadows, / And all my light has wept itself away.”
This error appears to have happened because the chatbot translated “apnā” – a reflexive possessive pronoun in Urdu – as “my,” inaccurately parsing it as referring to the speaker instead of the moons.
Finally, and most importantly, AI models lack the ability to express emotion the way a human can. A machine with no bodily experience of being human cannot meaningfully perceive a poem so enmeshed in human experience. Its engagement is merely superficial.
In its attempt to convey the mood of the original piece, ChatGPT offers: “From its dew in quiet, / A few drops rest upon your brow, / And glitter like tiny diamonds.”
It’s clear that ChatGPT is struggling to decode the grammatical structure of the poem and is trying to make the text lyrical enough to convey the awe and wonder of the original. But the model’s contrivances toward the lyrical – for example, describing diamonds as “tiny” or “glittering” – have no relation to the original poem.
“From its dew in quiet” is an incoherent clause. The phrase that seems to have thrown the model off is “isī kī shabnam se khāmoshī ke yeh cand qaṭre,” or “its dew / has rained drops of silence.”
Urdu literary critic Shamsur Rahman Faruqi has explained how Urdu poets “treat metaphor as fact and then go on to create further metaphors from that fact.” In “Meeting,” the metaphor of the night of the reunion as a tree becomes a fact, which allows for the flowering of a new metaphor – that of the dew on its leaves as drops of silence that fall on the lover and their beloved. These silences, heavy with sorrow, then adorn the beloved like precious jewels, conveying the idea that only a profound grief can beget such beauty.
The model has failed at conjuring this sense of wonder because it cannot parse the poem in accordance with the literary conventions of Urdu poetry.
ChatGPT prefaced its translated text by assuring us that it had “crafted a lyrical, poetic English version of Faiz’s ‘Mulāqāt,’ keeping the imagery, rhythm, and emotional flow intact so it reads like a poem rather than a literal translation.”
Yet as we have shown, its translation fails to accomplish the most basic task of literary translation: to convey the heart of the original.
Chatbots, in other words, are a poor substitute for the literary translator, and they bolster the assertion of the late Indian poet, scholar and translator A.K. Ramanujan that “only poems can translate poems.”
Adeeba Shahid Talukder helped with the research and writing of this article, in addition to the translation of Faiz’s poem."
https://theconversation.com/the-art-of-literary-translation-exposes-the-limits-of-ai-282955
#metaglossia
#metaglossia_mundus
"«Chiche kebab para tutti», «Bee do bee do bee do», «Poulet tikka masala»... Fidèles, irrésistibles et maladroits, les Minions ne parlent pas notre langue, et pourtant, nous comprenons certains de leurs mots.
Et pour cause, d’après Pierre Coffin, le créateur de ces adorables personnages en salopettes bleues et de leur étrange dialecte, il s'agit d’un mélange de français («tu pues des bras», «pignouf»), d’espagnol, d’italien et d’anglais («bello» pour «hello»).
Les Minions utilisent également certains mots japonais («como taki ?» pour «comment ça va?», «kampaï» pour «santé !») et comptent en coréen (hana, dul, set...).
une langue universelle
Dans une même phrase, Pierre Coffin s'amuse à assembler plusieurs mots qui n’ont aucun rapport entre eux et qui sont donc issues de différentes langues, ce qui donne le langage minion, un charabia délirant qui doit quand même coller à l'action et dont on doit comprendre globalement le sens.
Ne soyez donc pas surpris si vous entendez «chipolata», «bido», «poopaye» ou encore le fameux «banana» quand vous vous replongerez dans la franchise, notamment à l'occasion de la sortie du long-métrage «Des minions et des monstres» ce mercredi 24 juin.
D’ailleurs, c’est Pierre Coffin lui-même qui double chaque Minion depuis le premier «Moi Moche et Méchant» (2010), et ce, dans une seule langue pour tous les pays. "
https://www.cnews.fr/culture/2026-06-23/les-minions-quelle-est-cette-langue-etrange-que-parlent-les-celebres-petits
#metaglossia
#metaglossia_mundus
"Mistral met à jour son IA de lecture de documents (OCR) et la pousse vers les manuscrits et les langues rares. Derrière l’outil pour développeurs, l’enjeu est très concret : numériser des montagnes d’archives, jusque dans nos administrations.
Un document n’est pas qu’un bloc de texte parfaitement ordonné, dans un format bien lisible : il a une mise en page, des tableaux, des signatures, parfois une note griffonnée dans la marge ou des caractères devenus illisibles avec le temps. Ces subtilités propres à l’ère du papier qui n’est définitivement pas derrière nous (coucou les expats qui doivent remplir leurs impôts au stylo), c’est exactement ce que Mistral dit vouloir faire comprendre à sa nouvelle IA, OCR 4, présentée le 23 juin 2026. Le français ne se contente plus de transformer une page scannée en texte, il cherche à en restituer la structure.
L’OCR, en pratique, (reconnaissance optique de caractères) existe depuis des décennies et n’a pas eu besoin de l’IA pour se démocratiser. La nouveauté ici tient au niveau de détail. D’après le blog spécialisé MarkTechPost, OCR 4 localise chaque bloc d’une page avec des cadres de détection, le classe par type (titre, tableau, équation, signature) et attribue un score de confiance à chaque mot. Ainsi, le système qui reçoit le résultat sait non seulement ce qui est écrit, mais où ça se trouve et à quel point la machine est sûre d’elle.
Mistral revendique un modèle compact qui prend en charge 170 langues, y compris des langues peu documentées, que la plupart des outils lisent mal, et tourne dans un seul conteneur pour être hébergé en interne. Le tarif est fixé à 4 dollars (environ 3,70 €) pour 1 000 pages, qui tombe à 2 dollars (environ 1,85 €) en mode traitement par lots."
https://www.numerama.com/tech/2283529-mistral-lance-ocr-4-une-ia-capable-de-dechiffrer-les-manuscrits-et-170-langues.html
#metaglossia
#metaglossia_mundus
"English translation brings Filipino novel 'Lumbay ng Dila' to new readers
As Philippine literature slowly gains international visibility, a pressing question emerges: How do stories rooted in specific places travel beyond the archipelago without losing their soul?
For Filipino author and literary scholar Genevieve Asenjo, that journey is taking shape through "Lumbay ng Dila" ("The Melancholy of the Tongue"), her award-winning novel originally written in Filipino and now being translated into English through a Dutch publication initiative.
The project is more than an expansion of readership. It is an opportunity to bring regional Filipino histories into global conversations without stripping away their complexity.
At a time when international audiences are increasingly curious about Philippine literature, Asenjo's work offers an important reminder: there is no singular Filipino story waiting to be discovered. There are many Philippines, each shaped by its own language, geography, and memory.
"Lumbay ng Dila" follows Sadyah Zapanta Lopez, a 28-year-old teacher in Manila whose life is disrupted by a headline from home. Her grandfather, former assemblyman Marcelo Nones Lopez, has been acquitted after a 21-year trial linked to the 1984 Guinsang-an Bridge Massacre.
The verdict revives a question that has haunted her since childhood: What happened to her mother, Teresa Zapanta Lopez, known in the movement as Kumander Rafflesia, who disappeared after the violence and the years of fear that followed?
Drawn back to Barasanan in Dao, Antique, Sadyah attempts to rebuild a life among kin and memory while opening Balay Sugidanun, a home for stories. Her journey takes her between the province and the city, and eventually to Bangkok with her lover, Priya Iyer. Along the way, she assembles documents, testimonies, and fragments of a fractured past.
What begins as a daughter's search for answers gradually expands into a meditation on inheritance and collective memory. The novel asks what happens when communities carry unresolved histories across generations and whether remembering can become a form of repair.
For Philippine literature, translation has never been a purely technical exercise.
The English translation of "Lumbay ng Dila" allows readers outside the Philippines to encounter a story deeply embedded in Antique's cultural landscape while preserving the textures that make it distinct.
Yet every act of translation carries difficult questions. How do you preserve emotional weight when languages hold different histories? How do you translate political memory without reducing its complexity? How do you retain rhythms and voices that belong to a particular place?
For Asenjo, these tensions are part of the process.
"My first thought was that the novel had found another tongue and reader. It is a given that something is lost in translation; at the same time, something is also gained. I was less worried about individual words than about rhythm, voice, context, and the layered coexistence of Kinaray-a, Hiligaynon, Filipino, and English within the novel. Yet these are the very things that make translation exciting," she said.
Her response reframes translation not as a compromise but as a creative encounter. The challenge is not to reproduce every word exactly but to preserve a way of seeing the world.
Throughout her career, Asenjo has advocated for the visibility of regional voices within Philippine literature.
Although "Lumbay ng Dila" was written in Filipino, its worldview is deeply informed by Western Visayas and Kinaray-a culture. Rather than presenting a singular version of the nation, the novel embraces the many identities that coexist within the archipelago.
Its themes of loss, displacement, inheritance, and longing resonate far beyond Antique while remaining faithful to the communities that inspired them.
The task of translation, therefore, is not to make the novel less local. It is to allow its locality to travel.
The Dutch publication initiative signals a broader shift in how Philippine literature circulates internationally.
For decades, only a limited number of Filipino literary voices reached foreign audiences. Today, works grounded in regional histories are beginning to find new pathways abroad.
That shift matters because it changes how the Philippines is understood internationally.
The country cannot be represented by a single language, a single historical narrative, or a single literary tradition. Works like "Lumbay ng Dila" reveal a Philippines that is multilingual, layered, and constantly negotiating its own past.
Beyond translation: Why Filipino stories are finding global readers
Still, Asenjo is careful not to place impossible expectations on literature.
"I do not expect readers to finish the novel understanding the Philippines. I am not sure any single book can do that. But I hope they meet Sadyah and, in following her search through family histories, political histories, and matters of the heart, recognize a familiar human predicament: none of us begins our story at the beginning, yet all of us must somehow continue."
The journey of The "Melancholy of the Tongue" will soon move beyond the page and into a shared literary space in Barcelona.
On June 27, readers will gather at The Philippine Club in Plaza Reial for an intimate presentation of the novel and a rare opportunity to meet Asenjo in person.
Through readings and a question-and-answer session, Asenjo will discuss the creative process behind the novel.
For those unable to attend in person, a Facebook livestream will make the event accessible to audiences around the world."
https://www.abs-cbn.com/lifestyle/people-culture-events/2026/6/24/english-translation-brings-filipino-novel-lumbay-ng-dila-to-new-readers-1659
#metaglossia
#metaglossia_mundus
"...If using large models to write papers before was just about polishing and compiling references for you, then this Project from Professor Ross Griebenow’s team at Stanford is like dropping a nuclear bomb in the empirical circles of social sciences and economics.
The greatest truth is the simplest; the heaviest sword has no edge. Its functions are straightforward. Feed in the raw dataset, and within 30 minutes, it can generate a complete DOCX paper complete with full Stata/R code and publication-quality charts.
It chains together EDA, variable definition, econometric model building (from OLS to advanced DID, regression discontinuity, causal forests) all using an Agent workflow.
Every chart it produces comes with 100% reproducible Stata, R, EViews source code underneath. How many low-quality paper mills and data drones’ jobs will this smash?
Data drones and paper ghostwriters are collectively facing unemployment countdown. Because from now on, for social science papers, AI handles all the entropy-increasing drudgery—humans only need to define the problem."
https://marginalrevolution.com/marginalrevolution/2026/06/translated-from-the-chinese.html
#metaglossia
#metaglossia_mundus
"The most transformative impact of AI is still ahead, says DeepMind's Demis Hassabis
Google DeepMind CEO Demis Hassabis said AI still lacks true creativity and long-term reasoning, but could unlock new forms of storytelling, scientific discovery and artistic collaboration in the future
25 Jun 2026 10:40 IST
New Delhi: As Artificial Intelligence becomes increasingly embedded in creative industries, questions around originality, authorship and artistic expression are moving to the forefront. At Cannes Lions, one session explored these issues through the lens of one of the world's leading AI researchers.
Speaking at “The Future of Creativity”, a fireside chat at Cannes Lions, Demis Hassabis, Co-Founder and CEO of Google DeepMind, outlined his vision for how AI could support human creativity while accelerating scientific discovery and reshaping industries. He was joined by Francine Lacqua, Anchor and Editor-at-Large at Bloomberg Television, with Scott Belsky, founder of A24 Labs and Chief Strategy Officer at Adobe, later joining the discussion.
Current state of AI
Reflecting on the current state of AI, Hassabis said the pace of development has been "relentless" over the past decade, but added that key challenges continue to exist in artificial general intelligence (AGI).
“I think there's still a couple of really big pieces missing from what I would call AGI,” he said. “One is long-term reasoning planning, and another is what you could call true creativity.”
According to Hassabis, creativity involves more than refining existing ideas. “Not just iterating on a known idea or remixing existing things, but actually coming up with something novel or new,” he said.
Expanding on what artificial general intelligence could ultimately look like, Hassabis said Google DeepMind has long defined AGI as “being a system that exhibits all the cognitive capabilities humans are capable of".
Drawing on his neuroscience background, he noted that replicating human intelligence remains a formidable challenge, pointing to the extraordinary efficiency and complexity of the human brain - this includes brain functions such as emotions, creativity, and dreaming.
Future with AI
While discussions around AI often focus on disruption, Hassabis suggested that both the opportunities and challenges are still unfolding.
“I think AI is perhaps a bit overhyped in the very near term,” he said. “But then over the medium long term, over the next 10, 15 years, it is still underappreciated how much transformation AI is going to create.”
He added that the technology could lead to “almost a new human era”.
As generative AI tools become increasingly capable of creating and editing content across text, images, audio and video, Hassabis argued that their value lies not just in generating outputs but in enabling a more intuitive creative process.
Particularly as multimodal systems become increasingly capable of generating and editing text, images, audio and video, Hassabis argued that one of the key advantages of these tools is the ability to collaborate with them using natural language, making the creative process more intuitive and iterative.
“If you didn't like some part of the image or you wanted to adjust it, you could just describe in natural language explaining what you want,” he said.
Offering a creator's perspective, Belsky said the industry's response to AI remains mixed. While some artists are actively experimenting with the technology and exploring new creative possibilities, others continue to approach it with skepticism.
Despite those concerns, Belsky suggested AI could eventually give rise to entirely new forms of entertainment and storytelling, enabling more personalised and interactive experiences for audiences.
The discussion also touched on the future of work, with Belsky noting that technological shifts have historically created new categories of jobs and creative opportunities. He argued that the professions shaped by AI may be difficult to predict today, much like many digital-era careers would have seemed unimaginable a generation ago.
Concluding with transparency
As AI-generated content becomes increasingly sophisticated, Hassabis emphasised that transparency would be critical to maintaining trust in the technology. He noted that Google DeepMind developed watermarking systems alongside its models to help identify AI-generated content.
“We developed watermarking technology,” he said, adding that generated content should ultimately be traceable through common industry standards.
Despite ongoing debates around AI's impact on creativity, both speakers expressed confidence that creators would continue to adapt to new tools and technologies. Hassabis suggested that future generations would ultimately shape how AI is integrated into creative work, while ensuring that the distinctly human qualities underpinning creativity remain intact."
https://bestmediainfo.com/mediainfo/advertising/the-most-transformative-impact-of-ai-is-still-ahead-says-deepminds-demis-hassabis-12101063
#metaglossia
#metaglossia_mundus
Marruecos: marroquí
Túnez: tunecino
Curazao: curazoleño
República del Congo: congoleño
Costa de Marfil: marfileño
Cabo Verde: caboverdiano
Entre las selecciones participantes de este Mundial, algunas generan dudas respecto a los gentilicios por tratarse de nombres compuestos o poco usuales para nuestros oídos. Revisamos algunos casos.
Algunos gentilicios de las selecciones participantes, según verificación con la RAE, son:
Haití: haitiano
Bélgica: belga
Países Bajos: neerlandés
Croacia: croata
Argelia: argelino
Costa Rica: costarricense
Nueva Zelanda: neozelandés
Cabo Verde: caboverdiano
Costa de Marfil: marfileño
Marruecos: marroquí
Túnez: tunecino
Curazao: curazoleño
República Checa: checo
República del Congo: congoleño
Costa de Marfil: marfileño
Cabo Verde: caboverdiano
Arabia Saudita: saudí o saudita
Jordania: jordano
Uzbekistán: uzbeko"
https://www.hoy.com.py/ocio/rae/2026/06/24/modo-mundial-caboverdiano-y-otros-gentilicios-que-tal-vez-no-conocias
#metaglossia
#metaglossia_mundus
"The launch of the first national digital Maltese dictionary begins
On 19 June, at the University’s Aula Magna in Valletta, the Department of Maltese at the University of Malta announced the launch of the first national digital Maltese dictionary.
A new chapter in the history of the Maltese language – on 19 June, the first national digital Maltese dictionary was launched.
The Department of Maltese at the University of Malta announced the start of the national digital dictionary project – an authoritative, modern reference resource that is accessible to everyone free of charge.
Maltese already has many printed dictionaries, but for the first time we will have a dictionary that everyone can access from anywhere, free of charge, and which we can continue to update that is the beauty of being online. It is not like having a printed dictionary, where once it is printed, that is the end of it; we can add new words and new meanings that enter the language. This way, the Maltese language can remain up to date and also enter the digital era.
PROF. MICHAEL SPAGNOL
The idea began two years ago, and thanks to experts in the fields of lexicography, linguistics, corpus linguistics, and information technology, a dictionary began to be developed that provides definitions in Maltese, English equivalents, grammatical information and pronunciation guides, examples based on the natural use of the language, idioms and phrases, and the origins of words.
In terms of structure, it will include the main entry word, for example ‘frisk’. The first innovative feature is that you have the audio – how the word is pronounced. (…) Then you have the meanings. ‘Frisk’ as a noun and ‘frisk’ as an adjective. We also include phrases, such as ‘frisk frisk’ or ‘frisk bħal ħassa’. We continue down to the etymology – where the word comes from."
By Maria Christina Mallia
June 20, 2026
Aqra bil- Malti
DWAYNE ELLUL
https://tvmnews.mt/en/news/the-launch-of-the-first-national-digital-maltese-dictionary-begins/
#metaglossia
#metaglossia_mundus
"The Doha Historical Dictionary of the Arabic Language has launched an automated text-to-speech service on its website, aimed at enhancing user experience and facilitating access to and use of the dictionary's content through multimedia tools.
In a statement issued on Sunday, the dictionary stated that the service enables users to listen to dictionary entries, definitions, and historical citations contained in the dictionary, including prose texts, poetry, and verses from the Holy Quran. The feature provides an additional means of interacting with and exploring the content, while enhancing accessibility for researchers, students, Arabic language enthusiasts, and non-native learners.
Executive Director of the Doha Historical Dictionary of the Arabic Language, Dr. Mohammed Al Obaidi said that the launch of the automated text-to-speech service comes as part of ongoing efforts to develop the dictionary's online services and enable users to verify the correct pronunciation of entries, definitions, and historical citations.
He noted that the service will broaden access to the dictionary's content, particularly for users who prefer audio formats or need to listen to texts while browsing and studying, thereby strengthening the presence of Arabic in the digital sphere and improving the accessibility and usability of lexicographical content.
Al Obaidi explained that users can activate the service directly from the dictionary entry page by clicking the designated play icon, allowing them to listen to entries in a clear automated voice that ensures accurate and high-quality pronunciation.
The Doha Historical Dictionary of the Arabic Language also reaffirmed its commitment to continuously developing its digital platform through adopting the latest technologies and introducing advanced services that enhance access to lexicographical content and enrich user engagement, further reinforcing the dictionary's position as a dynamic knowledge project that keeps pace with rapid technological developments. (QNA)"
https://qna.org.qa/en/news/news-details?id=doha-historical-dictionary-launches-text-to-speech-feature-on-its-website&date=21/06/2026
#metaglossia
#metaglossia_mundus
"The Global Interpretation & Translation Market Study, a comprehensive analysis of the market that spans more than 143+ pages and describes the product and industry scope as well as the market prognosis and status for 2026-2034. The marketization process is being accelerated by the market study's segmentation by important regions. The market is currently expanding its reach.
Key Players in This Report Include:
TransPerfect, LanguageLine Solutions, RWS Group, Lionbridge Technologies, Welocalize, CyraCom International, Acolad Group, Thebigword Group, Hanna Interpreting Services, Propio Language Services, AMN Language Services, CTS LanguageLink.
Unlock the Report Insights 👉
https://www.htfmarketreport.com/sample-report/4395679-interpretation-translation-market
HTF Market Intelligence projects that the global Interpretation & Translation market will expand at a compound annual growth rate (CAGR) of 6.9 % from 2026 to 2034, from 62.50 Billion in 2025 to 108.40 Billion by 2034.
Our Report Covers the Following Important Topics:
By Type
Simultaneous Interpretation; Consecutive Interpretation; Remote Interpretation; Translation Services; Localization Services
By Application
Healthcare & Medical; Legal & Court Proceedings; Business Conferences; Government & Diplomacy; Education & Training
Definition:
The interpretation and translation industry provides language conversion services for spoken and written communication, enabling effective interaction across different languages in business, legal, healthcare, and public sectors.
Dominating Region:
• North America
Fastest-Growing Region:
• Asia-Pacific
Market Drivers
🔹 Growing international business activities and multilingual workforce environments.
🔹 Increasing demand for language support in healthcare, legal, government, and education sectors.
🔹 Expansion of global conferences, virtual meetings, and cross-border collaborations.
🔹 Rising migration and cultural diversity creating greater communication needs.
Market Trends
🔹 Adoption of remote interpretation platforms and virtual language services.
🔹 Integration of AI and speech recognition technologies to support interpreters.
🔹 Growing demand for on-demand language services across digital communication channels.
🔹 Increased use of hybrid human-machine translation workflows.
Market Challenges
🔹 Shortage of qualified interpreters for specialized and less-common languages.
🔹 Maintaining linguistic accuracy in real-time interpretation environments.
🔹 Data security concerns when handling confidential conversations and documents.
🔹 Pricing pressure due to increasing availability of automated language technologies.
Market Opportunities
🔹 Expansion of remote interpretation services for global events and virtual workplaces.
🔹 Growing demand for specialized interpretation in healthcare, legal, and technical industries.
🔹 Development of AI-enhanced language platforms supporting real-time communication.
🔹 Rising investments in multilingual customer support and international business services.
Need Research Tailored to Your Business Goals? Request a Custom Study 👉
https://www.htfmarketreport.com/enquiry-before-buy/4395679-interpretation-translation-market
Geographically, the detailed analysis of consumption, revenue, market share, and growth rate of the following regions:
• The Middle East and Africa (South Africa, Saudi Arabia, UAE, Israel, Egypt, etc.)
• North America (United States, Mexico & Canada)
• South America (Brazil, Venezuela, Argentina, Ecuador, Peru, Colombia, etc.)
• Europe (Turkey, Spain, Turkey, Netherlands Denmark, Belgium, Switzerland, Germany, Russia UK, Italy, France, etc.)
• Asia-Pacific (Taiwan, Hong Kong, Singapore, Vietnam, China, Malaysia, Japan, Philippines, Korea, Thailand, India, Indonesia, and Australia).
Order Full Report Now 👉 https://www.htfmarketreport.com/reports/4395679-interpretation-translation-market
Interpretation & Translation Market Research Objectives:
Focuses on the key manufacturers, to define, pronounce and examine the value, sales volume, market share, market competition landscape, SWOT analysis, and development plans in the next few years.
- To share comprehensive information about the key factors influencing the growth of the market (opportunities, drivers, growth potential, industry-specific challenges and risks).
- To analyze the with respect to individual future prospects, growth trends and their involvement to the total market.
- To analyze reasonable developments such as agreements, expansions new product launches, and acquisitions in the market.
- To deliberately profile the key players and systematically examine their growth strategies.
FIVE FORCES & PESTLE ANALYSIS:
Five forces analysis-the threat of new entrants, the threat of substitutes, the threat of competition, and the bargaining power of suppliers and buyers-are carried out to better understand market circumstances.
• Political (Political policy and stability as well as trade, fiscal, and taxation policies)
• Economical (Interest rates, employment or unemployment rates, raw material costs, and foreign exchange rates)
• Social (Changing family demographics, education levels, cultural trends, attitude changes, and changes in lifestyles)
• Technological (Changes in digital or mobile technology, automation, research, and development)
• Legal (Employment legislation, consumer law, health, and safety, international as well as trade regulation and restrictions)
• Environmental (Climate, recycling procedures, carbon footprint, waste disposal, and sustainability)
Unlock Up to 25% Savings on Your Purchase Today 👉 https://www.htfmarketreport.com/request-discount/4395679-interpretation-translation-market
Points Covered in Table of Content of Global Interpretation & Translation Market:
Chapter 01 - Interpretation & Translation Market Executive Summary
Chapter 02 - Market Overview
Chapter 03 - Key Success Factors
Chapter 04 - Global Interpretation & Translation Market - Pricing Analysis
Chapter 05 - Global Interpretation & Translation Market Background or History
Chapter 06 - Global Interpretation & Translation Market Segmentation (e.g. Type, Application)
Chapter 07 - Key and Emerging Countries Analysis Worldwide Polyester Fiber Market
Chapter 08 - Global Interpretation & Translation Market Structure & worth Analysis
Chapter 09 - Global Interpretation & Translation Market Competitive Analysis & Challenges
Chapter 10 - Assumptions and Acronyms
Chapter 11 - Interpretation & Translation Market Research Method Polyester Fiber
Thank you for reading this post. You may also obtain report versions by area, such as North America, LATAM, Europe, Japan, Australia, or Southeast Asia, or by chapter.
Nidhi Bhawsar (PR & Marketing Manager)
HTF Market Intelligence Consulting Private Limited
Phone: +15075562445
sales@htfmarketintelligence.com
About Author:
HTF Market Intelligence Consulting is uniquely positioned to empower and inspire with research and consulting services to empower businesses with growth strategies, by offering services with extraordinary depth and breadth of thought leadership, research, tools, events, and experience that assist in decision-making."
https://www.htfmarketreport.com/enquiry-before-buy/4395679-interpretation-translation-market";
https://www.openpr.com/news/4556350/interpretation-translation-market-may-see-a-big-move-major
#metaglossia
#metaglossia_mundus
"Considering one's own language as being superior to someone else’s exposes the narrowness of one’s own mind
Pratik Bapat 18 June, 2026 04:26 pm IST
Not too long ago, Mumbai had its municipal elections. With it came the ‘once-in-five-years’ attempts by political parties to remind voters how their language was under threat from an increasing influx of outsiders. The central point of debate around who would become mayor was whether they would be a Maharashtrian or not.
Some people were “slapped” for not speaking in Marathi. Every party has gone out of its way in recent elections to remind voters that they ought to vote for them because they are the so-called protectors of the language, and therefore, the people of the state. This is not only the case in Maharashtra, but in many other states where language has become a source of polarisation on par with caste and religion.
As a polyglot, this phenomenon is rather strange. I am a native Maharashtrian who learned to speak fluent English and Hindi through education and interaction. I began learning Spanish in high school and now possess a B2 (professional fluency) level certification. I have also learned some French (A1) and Mandarin (HSK 1-speaking). I can say with certainty that no language needs any political party’s protection. Each language is beautiful in its own way and some expressions in one language cannot be translated into another language.
Let us take the example of age. In English, you ‘are’ of a certain age, but in Spanish you ‘have’ so many years. In Hindi and Marathi, a person ‘is’ of a certain age, but in French, a person ‘has’ a certain age. Something as simple as age is expressed so differently in different languages.
Knowing more than one language gives a person the chance to acquire diverse conceptual maps of the world. If someone spoke a different language, I would want to learn theirs and speak theirs as well as I can speak mine. However, some people seem to be having a rather flabbergasting approach to this. They would rather hate someone who speaks another tongue.
No great city in the world is great because only one kind of language is spoken there. Most international level cities harbour diverse crowds. Geneva is in the French speaking part of Switzerland but you don’t just hear French there. You also hear a lot of Spanish, English, German, Mandarin, other European languages and, sometimes, also Hindi. It is the ability of cities to assimilate diverse crowds that determines a city’s ability to tap into a wide pool of talent in its workforce. In India, cities like Bangalore and Mumbai have become hubs because of their ability to utilise blue and white collar labour from other states. Linguistically monoclonal cities will never reach those heights.
It is sad to see language used as a political weapon. It is not necessary for a person to hate Hindi in order to love Marathi or vice versa. In fact, both are similar languages and can easily be learned by speakers of the other. Learning languages increases the plasticity of one’s mind and is never a minus in life. If this is not enough, let us remember that the leaders who divide voters on the lines of language often send their kids to English-medium international schools. I am sure that their kids learn German and French alongside English. However, they want their voters to be narrow minded because that suits their politics.
In a country of diverse languages, urban centres must strive to become as linguistically diverse as possible so as to attract talent from all over the country.
Pratik Bapat is a student of Geneva Graduate Institute.
https://theprint.in/campus-voice/the-futility-of-linguistic-chauvinism/2963210/?amp
#metaglossia
#metaglossia_mundus
"French and Spanish success in the Anthea Bell Translation Competition
Translation Competition
The Anthea Bell Prize for Young Translators was launched in 2020 by the Translation Exchange at The Queen’s College, Oxford. The competition is inspired by the work of the translator, Anthea Bell OBE (1936–2018), one of the finest and most influential literary translators of the 20th and 21st centuries, best known for her witty translations of the Asterix comic books. Not only did she translate works from French but also from German and Danish, tackling major works of European literature, including Kafka and Sebald.
The competition was founded to promote language learning across the UK, to inspire creativity in the classroom and to motivate more pupils to study modern foreign languages throughout their schooling and beyond.
It runs across four levels in six languages, French, German, Russian, Mandarin, Spanish and Italian. There are close to 25,000 entries every year and this year, pupils of French and Spanish were highly commended for their translations. Albert P in Year 10 translated an extract from Marguerite Audoux’s 1911 novel Marie-Claire and Clementine F and Evie J translated an extract from the Chilean author, José Ignacio Valenzuela’s, Mi Tío Pachunga. With close to 25,000 entries per year, this is a superb achievement for our pupils."
18 June 2026
https://www.greshams.com/french-and-spanish-success-in-the-anthea-bell-translation-exchange-competition-2026/
#metaglossia
#metaglossia_mundus
Transync AI Highlights New 2.0 Models for Faster, More Natural Multilingual Meetings
"As global teams increasingly rely on Zoom, Microsoft Teams, Google Meet, and other online meeting platforms, real-time translation is becoming an important part of daily collaboration.
Cross-language meetings, however, are rarely as simple as translating one complete sentence at a time. Real conversations often include short phrases, interruptions, background noise, mixed-language speech, and irregular pauses. These conditions can make traditional translation systems feel slow or inconsistent.
Transync AI has introduced its new 2.0 translation models to make multilingual meetings faster, more stable, and more natural.
New Translation Models Built for Real Conversations
The update includes upgraded versions of three Transync AI models: Gale 2.0, Monsoon 2.0, and Jetstream 2.0.
Each model has been improved to deliver better translation speed, accuracy, and continuity across different communication scenarios. The new models are especially optimized for the challenges that commonly occur in real meetings, including:
Short or incomplete sentences
Mixed-language speech
Background noise
Irregular sentence breaks
Fast exchanges between speakers
These improvements are designed to help translations remain easier to follow during active conversations, rather than only during prepared speeches or presentations.
Supporting Faster Multilingual Collaboration
Transync AI provides bidirectional real-time translation in 60 languages. Participants can speak in either of the two selected languages, while the system automatically identifies the language being spoken and translates it into the other.
The original speech and translated text are displayed side by side, giving users a clear view of both versions of the conversation. Translated voice playback is also available for users who prefer listening instead of continuously reading subtitles.
For online meetings, Transync AI works alongside platforms such as Zoom, Microsoft Teams, and Google Meet. As a standalone application, it does not need to appear as a participant bot inside the meeting.
This makes it suitable for international project meetings, overseas client calls, product demonstrations, remote training, and communication between regional offices.
More Natural Voice Translation
The v2.0 update also adds voice preview for AI broadcast.
Users can listen to different voice options before starting a meeting and choose one that better fits the situation. This can be useful when teams want a professional voice for client meetings, a clearer voice for training, or a more natural tone for everyday conversations.
Transync AI also supports multiple voice styles and voice cloning, allowing translated speech to sound more personal and consistent.
Better Support for Professional Terminology
Names, brand terms, technical phrases, and industry-specific vocabulary are common sources of translation errors.
To address this, Transync AI allows users to enter keywords and meeting context before a session begins. Teams can add company names, product names, professional terms, or personal names, while also describing the meeting topic or industry background.
The latest update expands the available keyword limits, giving individuals and enterprise users more room to prepare specialized vocabulary for professional discussions."
https://markets.financialcontent.com/stocks/article/abnewswire-2026-6-20-transync-ai-highlights-new-20-models-for-faster-more-natural-multilingual-meetings
#metaglossia
#metaglossia_mundus
The translated work, "The Stolen Bicycle" (單車失竊記), was made possible through the efforts of IBDE's Abdullah Hussaini,
"Malaysian publishing house promotes Taiwan literature to Malay readers
Kuala Lumpur, June 20 (CNA) A project manager at a publishing house in Malaysia said Saturday that he hopes to introduce literature from Taiwan to more Malay readers, following its first Malay-language translation of a work by author Wu Ming-yi (吳明益).
The translated work, "The Stolen Bicycle" (單車失竊記), was made possible through the efforts of IBDE's Abdullah Hussaini, who said he hopes the Malay edition will help more Malay readers discover the diversity of Taiwanese literature and deepen literary exchanges between Taiwan and Malaysia.
In an interview with CNA, Abdullah said IBDE has previously translated works from Arabic, French, German and English into Malay, but introducing a full-length Taiwanese novel to Malay readers remained a new venture for his publishing firm.
The book was featured at this year's Kuala Lumpur International Book Fair (KLIBF), held from May 29 to June 7.
IBDE project manager Abdullah Hussaini. CNA photo June 20, 2026
Originally published in Chinese in 2015, the novel tells the story of a man searching for his missing father and a lost bicycle, while weaving together stories of memory and reality across China, Myanmar, Japan and Taiwan. It also explores the wartime experiences and historical wounds of Taiwan's different communities.
Abdullah said he first heard about Wu about 10 years ago and was introduced to his works again by friends in the Malaysian Chinese literary circle three years ago.
He later attended Wu's talk at the George Town Literary Festival in Penang, where he began reading his works and was particularly impressed by "The Stolen Bicycle."
Abdullah said he felt a personal connection with the book, and that many of its themes also resonated with Malaysian social experiences.
During the interview, he thanked the Taipei Economic and Cultural Office in Malaysia for helping him reach out to Wu, saying he hopes to continue working with the office to promote other Taiwanese works in Malaysia.
Chinese-Malay translator Lee Hao Jie. CNA photo June 20, 2026
Lee Hao Jie (李浩傑), a translator of works from Chinese to Malay, including "Journey to the West" (西遊記), said the biggest challenge in bringing Taiwanese works into the Malay market is not language, but adapting cultural references.
Many Chinese-language works contain historical contexts, place names and cultural references, and the key challenge for translators is how to preserve the spirit of the original while enabling Malay readers to understand and relate to the text, Lee said.
Translators serve not only as converters of text but also as bridges between languages and cultures, he added.
(By Huang Tzu-chiang and Ko Lin)
Enditem/ASG"
06/20/2026 06:19 PM
https://focustaiwan.tw/culture/202606200011
#metaglossia
#metaglossia_mundus
"Never before have translators faced such immense pressure to become obsolete as they do today. AI tools capable of translating tens of thousands of words in just a few seconds at virtually no cost have significantly altered the landscape of the translation market.
In the context of globalization, translated literature serves as a bridge connecting the finest aspects of human knowledge to domestic readers, while simultaneously paving the way for local culture to reach the world . However, with the development of artificial intelligence (AI) and the pressures of the market economy, this field is facing numerous challenges.
Translator Pham Duc Hung edited the manuscript.
That impact is evident right here in Thai Nguyen . German translator Pham Duc Hung, a member of the Thai Nguyen Provincial Union of Literature and Arts Associations, a member of the Vietnam Writers Association since 2018, and the only German translator in the 10th term of the Literary Translation Council, has had to make the decision to close his reputable personal translation center in 2025 after many years of operation.
That story reflects a thought-provoking reality: Amidst a vibrant market for translated books, translators cannot make a living from their profession. Limited compensation hinders professional development in this field. Many people with strong foreign language skills are shifting to commercial or legal translation to earn a more stable income.
However, it is precisely under such pressure that the inviolable boundary between humans and machines is affirmed. Translator Pham Duc Hung points out a reality: AI can only translate documents, but literary translation requires human emotion and sensitivity. Idioms, proverbs, dialects, or the layers of cultural meaning hidden behind words are things that machines find difficult to fully convey.
Having ventured into translation in 2005, he has quietly amassed a considerable body of work with 8 published books on literature and skills (The Buried Candle, The Deruga Case, The Child of the Age, Outstanding Short Stories from Around the World, The Wheel of Fate, Money is Useless...) along with hundreds of short stories and poems by many German authors published in central and local newspapers and magazines.
A Harvard professor and a Vietnamese poet are working together on a project to translate The Tale of Kieu into English.
The successful translation also yielded positive results when the novel *The Deruga Affair* was honored with the Thai Nguyen Provincial Literature and Arts Award for the period 2017-2021.
However, producing such valuable translations requires a team of translators with a deep understanding of the language, culture, and literature. In Thai Nguyen, despite possessing a wealth of language experts from universities, the field of literary translation in the locality remains relatively quiet and largely spontaneous.
Preserving the essence of Vietnamese literature in the face of algorithms is difficult enough; figuring out how to perform the "reverse translation" task, bringing the indigenous literary and cultural resources of the Tea region to the world in the digital age, is an even greater concern.
Associate Professor Tran Thi Viet Trung (Critical and Critical Studies Branch, Union of Literature and Arts Associations of Thai Nguyen Province) believes that: To develop translation resources and bring the literature and culture of the tea-growing region to the world, there needs to be a mechanism for commissioning translations from the State, while also encouraging foreign students learning Vietnamese to participate in translating works into their languages.
Clearly, promoting local culture internationally cannot rely solely on the dedication and resources of translators. For local literary works to reach international readers, support in terms of mechanisms, publishing partnerships, and large-scale promotion is necessary.
This also includes training a team of translators, developing specialized translation models linked to universities, and implementing policies to encourage international students and researchers to participate in translating Vietnamese works into their own languages."
Báo Thái Nguyên
21/06/2026
https://www.vietnam.vn/en/van-hoc-dich-va-nhung-noi-niem-tran-tro
#metaglossia
#metaglossia_mundus
Lithuanian translator wins Metų vertėjo krėslo 2026 for translating Vasyl Shkliar’s novel
Sunday, 21 June 2026, 09:44
The Lithuanian translator of Ukrainian literature Donata Rinkevichenė became a laureate of the Metų vertėjo krėslo 2026 prize for the translation of Vasyl Shklyar’s novel “The Rabbit Church”.
According to Chytomo, the laureate was recognized for exceptional translation and the ability to convey the historical context of the work. The award ceremony took place with the participation of the Lithuanian PEN Center and the Ministry of Culture of Lithuania; the ceremonial act occurred in the hall of the Library of Vilnius University.
The awarding process and significance of the prize
The prize was presented by Lithuania’s Minister of Culture Vaida Aleknavičienė; the jury highlighted Rinkevichenė’s meticulous work, linguistic sensitivity and the richness of the translation, and also expressed gratitude for the opportunity for Lithuanian readers to see Ukrainian historical experience through literary fiction.
This award is a recognition of the highest translation mastery, and at the same time a thank you for the bridges built between Lithuania’s and Ukraine’s historical experience. The book “The Rabbit Church” tells of the joint resistance to empire, and today, as Ukraine continues to bravely defend its freedom, this work gains an even deeper significance
– Vaida Aleknavičienė
In 2025, the Lithuanian edition of the novel appeared in a publication by the Lithuanian Writers’ Union.
Donata Rinkevichenė has been translating from Ukrainian for six years. Among her translations are “Hemingway Knows Nothing” by Artur Dron, “The Age of Red Ants” by Tetiana Pyankova, “Carbide” by Andriy Liubka, “Who Are You?” by Oleksandra Myheda, “Codename for Job” by Oleksandra Myheda, the children’s book “36 and 6 Cats” by Halyna Vdovichenko, the publication Romana Romanyshyn and Andriy Lesiv’s “The War That Changed Rondo,” as well as texts in the anthology “Martial Law” and others.
Metų vertėjo krėslo is one of the most prestigious prizes in the field of literary translation in Lithuania. Laureates are awarded a diploma, a monetary prize, and a symbolic chair, which symbolizes the translator’s solitary work; each year the chair has a different design. The tradition is supported by poet and patron Gintaras Bleizgis.
Participants in this competition note that the prize highlights the significant contribution of translators to intercultural dialogue and allows Lithuanian readers to become acquainted with Ukrainian historical prose through high-quality translation."
https://mezha.net/eng/bukvy/ad2ebffc_lithuanian_translator_wins/
#metaglossia
#metaglossia_mundus
"When most English-speaking readers knew little about contemporary Chinese literature, one British publisher set out to change that. In this episode, we sit down with veteran publisher and translator Martin Savery, whose decades-long career has helped bring contemporary Chinese literature to English-speaking readers around the world. In an era dominated by short videos, social media, and shrinking attention spans, why does he still believe in books? And what can stories reveal about China that headlines cannot? Don't miss out!"
https://www.modernghana.com/amp/videonews/669497
#metaglossia
#metaglossia_mundus
"This article examines translation alignment patterns in parallel corpora of ancient and historical languages, derived from Ugarit, a crowdsourcing platform designed to manually align texts in low-resourced languages. The study analyzes bilingual alignments involving languages such as Ancient Greek, Latin, Classical Persian, Coptic, and Georgian, focusing on the ratios of word correspondences classified as one-to-one, one-to-many, many-to-one, and many-to-many. Findings indicate that linguistic structures—such as inflection and agglutination—and cultural factors, including translation practices and textual genres, significantly influence alignment patterns; for example, English translations of Classical Persian often show expansions and paraphrases reflecting cultural tendencies, while Georgian’s polysynthetic nature leads to different alignment dynamics with Ancient Greek. The research highlights the complex interplay between linguistic typology, cultural context, and translation strategies in the creation of aligned corpora, offering insights valuable for developing training data and guidelines for automatic translation models in ancient language studies.
Authored By: Palladino, Chiara; Yousef, Tariq 3 of 3
Authored By:
Palladino, Chiara;
Yousef, Tariq
Abstract
Source:
Digital Scholarship in the Humanities. 2023/09, Vol. 38, Issue 3, p1200
Document Type:
Article
Subject Area:
Language and Linguistics
Publication Date:
2023
ISSN:
2055-768X"
https://www.ebsco.com/articles/language-and-linguistics/76345535-69d4-5904-9188-480dc1a2aa2c/to-say-almost-the-same-thing-a-study-on-cross-linguistic-variation-in-ancient-texts-and-their-translations
#metaglossia
- #metaglossia_mundus
"...Accuracy does not guarantee understanding
So, what if the translation is technically correct but the participant still has to ask the site team what it really means? This is where localisation becomes essential.
It would be easy to assume a correctly translated sentence automatically conveys the intended meaning. In clinical research, this assumption can create challenges.
Before localisation even begins, we carefully craft the master document with the right tone, turning complex medical language into clear, plain English. Right from the start, this approach helps make our materials easier to understand. Once that solid foundation is set, our localisation experts adapt the content for each target language, making sure phrasing and sentence structures flow naturally while preserving the necessary medical accuracy. Ultimately, this process bridges the gap between technical correctness and real participant understanding.
How tone and intent shift across borders
Language is deeply tied to culture. What sounds polite and encouraging in one country might sound demanding or inappropriately casual in another.
For example, in some cultures, participant-facing materials are expected to use highly formal language, while in others a more conversational, approachable style is preferred. If materials written in plain English are directly translated without adapting the tone, they can come across as either too informal or overly authoritative, depending on the context. Localising content carefully adapts not just the words but the underlying intent, making sure it resonates with local expectations and, most importantly, helps foster participant trust.
Why right can still feel wrong
Even with perfect grammar, content can still feel unnatural. Best-practice research on translation and cultural adaptation in clinical studies has long shown that concepts and phrasing may need to be adapted, not just translated, to remain meaningful and relevant for the target audience. A recent study by Gregório et al. (2025) is one of many to evidence this.
Idiomatic expressions or metaphors used to explain how a drug works rarely cross borders intact. A ‘lock and key’ metaphor makes perfect sense to an English speaker, but it might have a totally different meaning in another region.
When trial participants read materials that feel distinctly foreign, they may question if the trial truly understands their needs. It’s vital that every piece of information reads as if it were written specifically for that local participant, in their own cultural context.
Spotting the warning signs
Poor translation can create operational challenges long before participants raise concerns directly. Trial teams may see the impact in added site queries, slower consent processes, misunderstandings around trial requirements and, over time, risks to protocol adherence and retention.
The value of getting it right
Standard translation gets your words across the border, but strategic localisation gets your meaning into the hands of the participant. We pride ourselves on delivering localised clinical trial materials that minimise confusion, reduce operational challenges and keep trials running smoothly.
Recognising where translation falls short is the first step. Next, we’ll look at what effective localisation actually looks like in practice."
https://pmlive.com/pmhub/cuttsycuttsy/where-translation-falls-short-in-practice/
#metaglossia
#metaglossia_mundus
"DeepL expands into Silicon Valley, adds Mixhalo team and technology to accelerate Voice AI at scale
2026-06-17
DeepL is bringing its real-time voice translation capabilities from meetings to the big stage with Mixhalo’s ultra-low latency audio technology – trusted by MLB, NASCAR, T-Mobile, Verizon and more
Marks the opening of DeepL’s first office in San Francisco, accelerating momentum in its fastest-growing market where nearly 50% of US Fortune 500 are users
COLOGNE, DE and SAN FRANCISCO, CA - June 17, 2026 - DeepL, a global leader in Language AI, today announced that the team and technology behind Mixhalo, the San Francisco-based platform for real-time, ultra-low latency audio, have joined DeepL. The investment expands the capabilities of DeepL Voice, the company’s real-time AI voice translation solution, to include larger and more complex environments where speed, clarity, and reliability are critical, including major events, conferences, customer support and business workflows.
DeepL Voice already leads the category in real-time voice translation for spoken conversations - from virtual meetings to in-person interactions- far outperforming Microsoft Teams, Zoom, and Google Meet on accuracy, fluency, and reliability with a 96.4/100 quality score and a 4% fail rate versus a 17% market average (2026 independent Slator assessment). With Mixhalo’s team and technology now part of DeepL, the company is integrating ultra-low-latency audio infrastructure into DeepL Voice to support live, large-scale environments. This enables translated speech and captions to reach audiences clearly and instantly, from smaller live settings to tens of thousands of attendees, while preserving the pace and natural fluency of live speech.
"DeepL Voice is already changing how people and businesses work across languages every day, and the Mixhalo team and technology let us bring this to even larger, more complex settings," said Jarek Kutylowski, Founder and CEO, DeepL. "The team has solved one of the hardest problems in live audio, which is delivering high-fidelity sound to thousands of people at once with basically zero latency. Together, we're building the real-time Language AI layer for communication, so people can understand each other naturally wherever they are interacting, whether that's in team meetings, customer calls or even major international events."
Founded in 2016 by Incubus guitarist and songwriter Mike Einziger, violinist Ann Marie Simpson-Einziger, and technologist Vik Singh, Mixhalo was built to reimagine how people experience live sound. Its platform delivers high-fidelity, synchronized audio to thousands of listeners simultaneously with extremely low latency, and has powered live audio across major sports, entertainment, and brand experience. Its work spans the MLB, NASCAR, EQUINOX, Verizon, T-Mobile, the Sacramento Kings, Red Rocks Park and Amphitheatre, and TSX; leading global events and conferences including the CES, Mobile World Congress, Salesforce’s flagship conferences, the Databricks AI Summit, and Microsoft AI Tour Paris; as well as concerts and residencies for artists including Metallica, Aerosmith, Sting and Charlie Puth.
“We launched Mixhalo to deliver the best quality audio to live audiences at any size, all within 20 milliseconds. As we expanded into real-time translation, the hardest part was finding technology that could keep up with live speech without compromising quality,” said Vik Singh, Co-Founder, Mixhalo. “After testing technology from nearly all of the leading providers, DeepL was the only one that could deliver accurate translations at the speed we needed to achieve real fluency. We’ve already seen what this combination can do in real-world settings, and by joining DeepL, we can now bring this experience to even more audiences and customers globally.”
DeepL and Mixhalo have already brought their combined technology to market, with the DeepL Voice API powering real-time translation across Mixhalo’s live-audio platform. The teams are also piloting customer support use cases through integrations like Amazon Connect.
“Voice AI is ultimately a fight for latency, quality, and real-world reliability,” said Sebastian Enderlein, CTO, DeepL. “The Mixhalo team has deep experience bringing APIs and audio infrastructure into live environments where there is no room for delay or failure. That expertise is incredibly valuable as we continue to scale DeepL Voice, and their presence in San Francisco brings us even closer to the customers, partners, and developer ecosystem shaping the next generation of AI products.”
The announcement also marks the opening of DeepL’s first San Francisco office, strengthening its footprint in the US, the company’s fastest-growing market. DeepL’s US customer base already includes NVIDIA, Cisco, and Nasdaq, and nearly 50% of the Fortune 500 are DeepL users.
Audiences will be able to experience this technology in action at GITEX Europe 2026 at the end of June, where DeepL will serve as the official translation partner, powering live German-to-English captions on the main stage. DeepL will also showcase its next-generation Voice AI capabilities live at upcoming US events including Databricks Data + AI Summit, Esri User Conference, and Salesforce Dreamforce.
About DeepL
DeepL is a global AI company building the language infrastructure that powers global business. More than 200,000 business teams and millions of individuals use DeepL’s Language AI platform to communicate globally, collaborate and operate across languages in real time. By combining breakthrough AI models with enterprise-grade security and privacy, DeepL enables organizations to work seamlessly across markets and cultures. Founded in 2017 by CEO Jarek Kutylowski, DeepL now has more than 900 employees and is backed by leading investors including Benchmark, IVP and Index Ventures. Learn more at www.deepl.com."
DeepL https://share.google/GGiA9di79kwonJzCY
|
"Bilingualism is Driven by a Single Neurological “Grammar Engine”
New study finds a common neural system builds a language across languages
NYU researchers have found that bilingualism is not powered by separate grammar engines in the brain, but, rather, by a common neural system that works across languages. Above: A restaurant in Silves, Portugal. Photo credit: Mary Salen/Getty Images
It’s not uncommon for bilingual speakers to mistakenly apply the grammatical rules of one language while speaking the other—for example, saying “I have 20 years” instead of “I am 20” when asked about their age.
Some may wonder if these language mashups are evidence of deeper neurological distinctions among languages: If you speak English and Spanish, for instance, do you have an English “grammatical engine” that learns and applies English rules and a Spanish one that learns and applies Spanish rules?
A new study by a team of New York University scientists finds that, in fact, bilingualism is not powered by separate grammar engines in the brain, but, rather, by a common neural system that works across languages.
“Our research suggests that brains have a single grammatical engine that fuels all of the languages we speak—rather than separate engines for each one,” explains Esti Blanco-Elorrieta, an assistant professor of psychology and neural science at NYU and the senior author of the study, which appears in JNeurosci. “We show that the same brain patterns support grammar in English and Spanish, indicating that human language may be built from neural computations that transcend any one language.”
While previous research has found neurological commonality across speakers of different languages and other NYU research has explored “bilingual brains,” less clear is how the brain builds grammar across languages in bilingual speakers.
To address this, Blanco-Elorrieta and Xuanyi Jessica Chen, an NYU doctoral student and the paper’s first author, used magnetoencephalography (MEG) to track brain activity millisecond-by-millisecond while Spanish-English bilingual speakers transformed both English and Spanish words into grammatically correct forms. For instance, participants would hear a singular form of a word (“boat” [English] or “barco” [Spanish]) and were asked to say the plural version of the term (e.g., “boats” or “barcos”).
We show that the same brain patterns support grammar in English and Spanish, indicating that human language may be built from neural computations that transcend any one language.
Esti Blanco-Elorrieta
Assistant Professor of Psychology
The researchers also tested how participants responded to both cognates—words in different languages that share a similar meaning, spelling, and pronunciation because of their common linguistic roots—and “pseudowords” (made-up words such as “paple”).
This method, which reached beyond existing words in English and Spanish, was aimed at determining if the same neural mechanisms apply when novel words enter our vocabulary.
The findings showed that the brain relies on a shared neural mechanism for grammar across languages, even when words differ in sound or structure. Moreover, the same neural system also applied to completely novel words (i.e., pseudowords), further suggesting that the brain implements grammar as a reusable computation—or universal language template—rather than deploying multiple language-specific rulebooks.
“The results provide some of the clearest neural evidence to date that grammatical computations are shared across languages in bilingual speakers,” says Blanco-Elorrieta, who previously teamed up with Chen to create a calculator to measure multilingualism. “More broadly, because the brain appears to use a common neural system across languages, our findings offer new insight into how we communicate and learn new languages.”
This research was supported by grants from the National Science Foundation (BCS-Grant 2446452) and the National Institutes of Health (R00 DC019973-01)."
Original publication date: Jun 15, 2026
https://www.nyu.edu/about/news-publications/news/2026/june/bilingualism-is-driven-by-a-single-neurological--grammar-engine-.html
#metaglossia
#metaglossia_mundus