#Linguistics
Latest news articles tagged with "Linguistics". Follow the timeline of events, related topics, and entities.
Articles (14)
-
🇬🇧 Children’s vocabulary shrinking as reading loses out to screen time, says Susie Dent
[United Kingdom]
<p>Exclusive: Countdown lexicographer urges families to read, talk and play word games to help language development</p><p>Children’s vocabulary is shrinking as reading loses out to screen time, accord...
Related: #Education, #Digital Health -
🇬🇧 Spanish is clearly now the world’s coolest language. So why do we push British children to learn French? | Gary Nunn
[United Kingdom]
<p>As Bad Bunny showed at the Super Bowl, español is the coming thing. No wonder it’s now the top GCSE language choice</p><p>“Now, Gary, repeat after me: <em>Quiero una margarita, por favor,” </em>my ...
Related: #Education, #Culture -
🇺🇸 Does Visual Rendering Bypass Tokenization? Investigating Script-Tokenizer Misalignment in Pixel-Based Language Models
[USA]
arXiv:2602.06973v1 Announce Type: cross Abstract: While pixel-based language modeling aims to bypass the sub-word tokenization bottleneck by rendering text as images, recent multimodal variants such ...
Related: #Artificial Intelligence, #Technology -
🇺🇸 A New Mode of Teaching Chinese as a Foreign Language from the Perspective of Smart System Studied by Using Rongzhixue
[USA]
arXiv:2602.06992v1 Announce Type: cross Abstract: The purpose of this study is to introduce a new model of teaching Chinese as a foreign language from the perspective of integrating wisdom. Its chara...
Related: #Education Technology, #Artificial Intelligence -
🇺🇸 Recontextualizing Famous Quotes for Brand Slogan Generation
[USA]
arXiv:2602.06049v1 Announce Type: cross Abstract: Slogans are concise and memorable catchphrases that play a crucial role in advertising by conveying brand identity and shaping public perception. How...
Related: #Artificial Intelligence, #Marketing -
🇺🇸 Generics in science communication: Misaligned interpretations across laypeople, scientists, and large language models
[USA]
arXiv:2602.06190v1 Announce Type: cross Abstract: Scientists often use generics, that is, unquantified statements about whole categories of people or phenomena, when communicating research findings (...
Related: #Science Communication, #Artificial Intelligence -
🇺🇸 CORE: Comprehensive Ontological Relation Evaluation for Large Language Models
[USA]
arXiv:2602.06446v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform well on many reasoning benchmarks, yet existing evaluations rarely assess their ability to distinguish between m...
Related: #Artificial Intelligence, #Data Science -
🇺🇸 MTQE.en-he: Machine Translation Quality Estimation for English-Hebrew
[USA]
arXiv:2602.06546v1 Announce Type: cross Abstract: We release MTQE.en-he: to our knowledge, the first publicly available English-Hebrew benchmark for Machine Translation Quality Estimation. MTQE.en-he...
Related: #Artificial Intelligence, #Technology -
🇺🇸 compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data
[USA]
arXiv:2602.06669v1 Announce Type: cross Abstract: Large Language Models (LLMs) often show reduced performance, cultural alignment, and safety robustness in non-English languages, partly because Engli...
Related: #Artificial Intelligence, #Digital Sovereignty -
🇺🇸 Halluverse-M^3: A multitask multilingual benchmark for hallucination in LLMs
[USA]
arXiv:2602.06920v1 Announce Type: cross Abstract: Hallucinations in large language models remain a persistent challenge, particularly in multilingual and generative settings where factual consistency...
Related: #Artificial Intelligence, #Data Science -
🇺🇸 Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay
[USA]
arXiv:2602.06942v1 Announce Type: cross Abstract: Tokenization is a pivotal design choice for neural language modeling in morphologically rich languages (MRLs) such as Turkish, where productive agglu...
Related: #Artificial Intelligence, #Data Science -
🇺🇸 ExpressivityBench: Can LLMs Communicate Implicitly?
[USA]
arXiv:2411.08010v2 Announce Type: replace-cross Abstract: Human communication is often implicit, conveying tone, identity, and intent beyond literal meanings. While large language models have achieve...
Related: #Artificial Intelligence, #Technology -
🇺🇸 EuroLLM-22B: Technical Report
[USA]
arXiv:2602.05879v1 Announce Type: cross Abstract: This report presents EuroLLM-22B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official E...
Related: #Artificial Intelligence, #Digital Sovereignty -
🇺🇸 The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models
[USA]
arXiv:2601.19926v1 Announce Type: cross Abstract: We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models, reporting on 1,015 model resu...
Related: #Technology, #AI research