Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition

• URL: http://arxiv.org/abs/2605.12047v1
• Date: Tue, 12 May 2026 12:26:50 GMT
• Title: Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition
• Abstract summary: We investigate whether child-directed language (CDL) is optimized to support language learning.<n>We show that models trained on CDL and spoken ADL show significantly higher resilience than those trained on written input.
• Score: 10.370896360498644
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Do Syntactic Categories Help in Developmentally Motivated Curriculum Learning for Language Models? [22.306066892204274]
  We examine the syntactic properties of BabyLM corpus, and age-groups within CHILDES.<n>While CHILDES does not exhibit strong syntactic differentiation by age, we show that the syntactic knowledge about the training data can be helpful in interpreting model performance on linguistic tasks.
  arXiv  Detail & Related papers  (2025-11-11T13:03:27Z)
• Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models [5.636296752147828]
  We show that language models trained on English Child-Directed Language (CDL) reach similar syntactic abilities as LMs trained on larger amounts of adult-directed written text.<n>We test this by comparing models trained on CDL vs. Wikipedia across two LM objectives (masked and causal), three languages (English, French, German), and three syntactic minimal-pair benchmarks.<n>Our results on these benchmarks show inconsistent benefits of CDL, which in most cases is outperformed by Wikipedia models.
  arXiv  Detail & Related papers  (2025-05-29T17:25:36Z)
• When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners [111.50503126693444]
  We show that language-specific ablation consistently boosts multilingual reasoning performance.<n>Compared to post-training, our training-free ablation achieves comparable or superior results with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-05-21T08:35:05Z)
• A Distributional Perspective on Word Learning in Neural Language Models [57.41607944290822]
  There are no widely agreed-upon metrics for word learning in language models.<n>We argue that distributional signatures studied in prior work fail to capture key distributional information.<n>We obtain learning trajectories for a selection of small language models we train from scratch.
  arXiv  Detail & Related papers  (2025-02-09T13:15:59Z)
• From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition [6.617999710257379]
  We propose a three-stage framework to assess the abilities of LMs. We evaluate the generative capacities of LMs using methods from linguistic research.
  arXiv  Detail & Related papers  (2024-10-17T06:31:49Z)
• A systematic investigation of learnability from single child linguistic input [12.279543223376935]
  Language models (LMs) have demonstrated remarkable proficiency in generating linguistically coherent text. However, a significant gap exists between the training data for these models and the linguistic input a child receives. Our research focuses on training LMs on subsets of a single child's linguistic input.
  arXiv  Detail & Related papers  (2024-02-12T18:58:58Z)
• Leveraging Code to Improve In-context Learning for Semantic Parsing [48.66031267718704]
  In-context learning (ICL) is an appealing approach for semantic parsing due to its few-shot nature and improved generalization. We improve the effectiveness of ICL for semantic parsing by (1) using general-purpose programming languages such as Python instead of DSLs, and (2) augmenting prompts with a structured domain description.
  arXiv  Detail & Related papers  (2023-11-16T02:50:06Z)
• Evaluating Neural Language Models as Cognitive Models of Language Acquisition [4.779196219827507]
  We argue that some of the most prominent benchmarks for evaluating the syntactic capacities of neural language models may not be sufficiently rigorous. When trained on small-scale data modeling child language acquisition, the LMs can be readily matched by simple baseline models. We conclude with suggestions for better connecting LMs with the empirical study of child language acquisition.
  arXiv  Detail & Related papers  (2023-10-31T00:16:17Z)
• Visual Grounding Helps Learn Word Meanings in Low-Data Regimes [47.7950860342515]
  Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension. But to achieve these results, LMs must be trained in distinctly un-human-like ways. Do models trained more naturalistically -- with grounded supervision -- exhibit more humanlike language learning? We investigate this question in the context of word learning, a key sub-task in language acquisition.
  arXiv  Detail & Related papers  (2023-10-20T03:33:36Z)
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity [68.8204255655161]
  We present the semantic notion of agentivity as a case study for probing such interactions. This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
  arXiv  Detail & Related papers  (2023-05-29T16:24:01Z)
• Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models [67.19567060894563]
  Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks. We present a new study investigating how well PLMs capture cross-lingual word sense with Contextual Word-Level Translation (C-WLT) We find that as the model size increases, PLMs encode more cross-lingual word sense knowledge and better use context to improve WLT performance.
  arXiv  Detail & Related papers  (2023-04-26T19:55:52Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation [127.81351683335143]
  Cross-lingual pretraining requires models to align the lexical- and high-level representations of the two languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language model pretraining with lexical-level information by using type-level cross-lingual subword embeddings.
  arXiv  Detail & Related papers  (2021-03-18T21:17:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.