language-acquisition
Filtering by topic language-acquisition(3)Clear all filters
- PaperComputer Assisted Language Learning11 Jun 2026
From declarative knowledge to procedural fluency: a generative AI tutor for Arabic agreement rules
Djemai Mahmoud Boulaares
This paper proposes a generative AI tutor designed to help Arabic learners transition from declarative knowledge of agreement rules to procedural fluency in applying them.
- PaperarXiv — Language & NLP (cs.CL)31 May 2026
Child-directed speech facilitates production, not comprehension, in BabyLMs
Bastian Bunzeck, Sina Zarrieß
Child-directed speech (CDS) boosts production in language models but not comprehension, as shown by a novel frame-completion task. While web-trained models excel on comprehension benchmarks, CDS-trained models produce grammatically correct completions earlier and concentrate probability on appropriate slot-fillers.
Original abstract
Recent studies suggest that child-directed speech is not conducive to language learning in BabyLMs. However, current evaluations focus predominantly on comprehension and not production, which is central to usage-based theories of language acquisition which argue how CDS facilitates early language use through constructional ''frames'' (frequent lexical patterns with open slots). We introduce a novel generation-based evaluation inspired by such theories in form of a frame-completion task, and compare Llama models trained with CDS, the BabyLM corpus, and web-crawl data (FineWeb-edu) on comprehension benchmarks and our novel framework. Our results reveal a clear dissociation between models' comprehension and production capabilities: while FineWeb-trained models excel at minimal pairs, CDS-trained models produce grammatical completions substantially earlier in training and concentrate probability mass on appropriate slot-fillers. These findings show that comprehension benchmarks underestimate what CDS affords to BabyLMs.
- PaperarXiv — Language & NLP (cs.CL)12 May 2026
Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition
Francesca Padovani, Jaap Jumelet, Yevgen Matusevych, Arianna Bisazza
Neural language models trained on child-directed language (CDL) versus adult-directed language (ADL) show that removing syntax impairs verb learning across datasets, but models trained on spoken input (including CDL) are more resilient. The study finds that verb meanings emerge before syntactic proficiency, especially in spoken CDL, suggesting that the advantage for verb learning attributed to CDL may reflect broader properties of spoken register rather than CDL-specific optimization.
Original abstract
Is child-directed language (CDL) optimized to support language learning, and which aspects of linguistic development does it facilitate? We investigate this question using neural language models trained on CDL versus adult-directed language (ADL). We selectively remove syntactic or lexical co-occurrence information from the model training data, and evaluate the impact of these manipulations on verb meaning acquisition. While disrupting syntax impairs learning across all datasets, models trained on CDL and spoken ADL show significantly higher resilience than those trained on written input. Tracking semantic and syntactic performance over training, we observe a semantic-first trajectory, with verb meanings emerging prior to robust syntactic proficiency, an asynchrony most pronounced in the spoken domain, especially CDL. These results suggest that the advantage for verb learning previously attributed to CDL may instead reflect broader properties of the spoken register, rather than a uniquely CDL-specific optimization.