arXiv:2603.02082v2 Announce Type: replace 
Abstract: Children's acquisition of filler-gap dependencies has been argued by some to depend on innate grammatical knowledge, while others suggest that the distributional evidence available in child-directed speech suffices. Unfortunately, the relevant input is difficult to quantify at scale with fine granularity, making this question difficult to resolve. We present a system that identifies three core filler-gap constructions in spoken English corpora -- matrix wh-questions, embedded wh-questions, and relative clauses -- and further identifies the extraction site (i.e., subject vs. object vs. adjunct). Our approach combines constituency and dependency parsing, leveraging their complementary strengths for construction classification and extraction site identification. We validate the system on human-annotated data and find that it scores well across most categories. Applying the system to 57 English CHILDES corpora, we are able to characterize children's filler-gap input and their filler-gap production trajectories over the course of development, including construction-specific frequencies and extraction-site asymmetries. The resulting fine-grained labels enable future work in both acquisition and computational studies, which we demonstrate with a case study using filtered corpus training with language models.

تم نشر دراسة جديدة تفحص اكتساب الأطفال للاعتماد على الفجوات في اللغة، باستخدام نظام يحدد البنى الأساسية في اللغة الإنجليزية المنطوقة. تركز الدراسة على أسئلة wh-المصفوفة، وأسئلة wh-المتداخلة، والعبارات النسبية، مستخدمة تقنيات تحليل متقدمة لتصنيف البنى وتحديد مواقع الاستخراج.

Se ha publicado un nuevo estudio que examina la adquisición de dependencias de relleno en los niños, utilizando un sistema que identifica construcciones clave en el inglés hablado. La investigación se centra en preguntas wh-matriz, preguntas wh-embebidas y cláusulas relativas, empleando técnicas de análisis avanzadas para clasificar construcciones e identificar sitios de extracción.

Une nouvelle étude a été publiée sur l'acquisition des dépendances de remplissage chez les enfants, utilisant un système qui identifie les constructions clés dans l'anglais parlé. La recherche se concentre sur les questions wh-matrices, les questions wh-imbriquées et les clauses relatives, en utilisant des techniques d'analyse avancées pour classifier les constructions et identifier les sites d'extraction.

A new study has been published examining children's acquisition of filler-gap dependencies in language, utilizing a system that identifies core constructions in spoken English. The research focuses on matrix wh-questions, embedded wh-questions, and relative clauses, employing advanced parsing techniques to classify constructions and identify extraction sites.

What Exactly do Children Receive in Language Acquisition? A Case Study on CHILDES with Automated Detection of Filler-Gap Dependencies

arXiv:2606.07422v1 Announce Type: new 
Abstract: Large language models are increasingly used to answer culturally grounded questions across languages, yet it remains unclear whether local cultural knowledge is better accessed through English or the local language. Existing evaluations face two key limitations: many rely on parallel template-based questions that may not reflect how cultural knowledge naturally appears, and raw accuracy conflates general language proficiency with language-conditioned knowledge access. We address these issues with a controlled framework built on real-world cultural questions collected from regional benchmarks and local sources. By crossing question type (culture-agnostic vs. culture-specific) with query language (English vs. local language), and estimating ability with a shared 1PL item response theory model, we separate proficiency from localized knowledge access. Across 13 locales and roughly 80 models, we find a consistent English advantage on culture-agnostic questions, indicating stronger English proficiency. However, after accounting for this proficiency gap, local languages show a positive knowledge-access advantage in nearly all locale-model settings. This advantage is often masked in raw accuracy but becomes more visible for frontier, regionally aligned, or language-adapted models. Our results suggest that weaker local-language performance does not necessarily imply weaker cultural knowledge; rather, local cultural knowledge may be more accessible through the local language but hidden by limited language proficiency.

دراسة حديثة نُشرت على arXiv تستكشف فعالية نماذج اللغة الكبيرة (LLMs) في الوصول إلى المعرفة الثقافية المحلية عبر لغات مختلفة، مع التركيز على مقارنة اللغة الإنجليزية واللغات المحلية. تحدد الأبحاث ميزة ثابتة للغة الإنجليزية في الوصول إلى المعرفة الثقافية عبر مناطق متنوعة، مما يبرز القيود الموجودة في التقييمات الحالية التي غالبًا ما تخلط بين الكفاءة اللغوية والوصول إلى المعرفة.

Un estudio reciente publicado en arXiv investiga la efectividad de los modelos de lenguaje de gran tamaño (LLMs) para acceder al conocimiento cultural local a través de diferentes idiomas, comparando específicamente el inglés y los idiomas locales. La investigación identifica una ventaja constante para el inglés en el acceso al conocimiento cultural en diversas localidades, destacando las limitaciones de las evaluaciones existentes que a menudo confunden la competencia lingüística con el acceso al conocimiento.

Une étude récente publiée sur arXiv examine l'efficacité des modèles de langage de grande taille (LLMs) pour accéder aux connaissances culturelles locales à travers différentes langues, en comparant spécifiquement l'anglais et les langues locales. La recherche identifie un avantage constant pour l'anglais dans l'accès aux connaissances culturelles à travers diverses régions, soulignant les limites des évaluations existantes qui confondent souvent la maîtrise linguistique avec l'accès aux connaissances.

A recent study published on arXiv investigates the effectiveness of large language models (LLMs) in accessing local cultural knowledge through different languages, specifically comparing English and local languages. The research identifies a consistent advantage for English in cultural knowledge access across various locales, highlighting limitations in existing evaluations that often conflate language proficiency with knowledge access.

The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs

arXiv:2606.06065v2 Announce Type: replace 
Abstract: Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural approach because it assumes that shared representations benefit both outputs. However, this paper shows that this assumption does not hold across Korean and English. MTL improves meaning but degrades surface transcription, especially in English, where the degradation scales with surface-meaning divergence measured by Levenshtein edit distance. Encoder analysis links these patterns to encoder-level entanglement, with Korean preserving distinct task representations while English produces nearly identical ones. Cross-task decoder analysis shows that the meaning dual-output decoder adapts with a unique representation, while the surface dual-output decoder remains constrained by the encoder. These findings motivate the design of MTL frameworks that mitigate encoder-level entanglement to reduce surface degradation in dual-output L2 automatic speech recognition.

تسلط دراسة حديثة الضوء على قيود التعلم المتعدد المهام (MTL) في التعرف على الكلام بلغة ثانية، خاصة بين الكورية والإنجليزية. تشير الأبحاث إلى أنه بينما يمكن أن يحسن MTL التعرف على المعاني، فإنه يؤثر سلبًا على دقة النسخ السطحي، خاصة في الإنجليزية، حيث ترتبط التدهورات بالتباين بين التمثيلات السطحية والمعنوية.

Un estudio reciente destaca las limitaciones del aprendizaje multitarea (MTL) en el reconocimiento de voz de segundas lenguas, especialmente entre el coreano y el inglés. La investigación indica que, aunque el MTL puede mejorar el reconocimiento de significados, afecta negativamente la precisión de la transcripción superficial, especialmente en inglés, donde la degradación se correlaciona con la divergencia entre las representaciones superficiales y de significado.

Une étude récente met en lumière les limites de l'apprentissage multitâche (MTL) dans la reconnaissance de la parole en langue seconde, en particulier entre le coréen et l'anglais. La recherche indique que, bien que le MTL puisse améliorer la reconnaissance des significations, il affecte négativement la précision de la transcription de surface, surtout en anglais, où la dégradation est corrélée à la divergence entre les représentations de surface et de signification.

A recent study highlights the limitations of multi-task learning (MTL) in second language speech recognition, particularly between Korean and English. The research indicates that while MTL can enhance meaning recognition, it adversely affects surface transcription accuracy, especially in English, where the degradation correlates with the divergence between surface and meaning representations.

What Exactly do Children Receive in Language Acquisition? A Case Study on CHILDES with Automated Detection of Filler-Gap Dependencies

Was this article worth reading? Share it

Ready to build your own newsroom?