Papers with CHILDES corpus
How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech (2023.acl-long)
Copied to clipboard
| Challenge: | LSTMs and Transformers perform well at capturing the surface statistics of child-directed speech, but both model types generalize in a way consistent with an incorrect linear rule than the correct hierarchical rule. |
| Approach: | They train LSTMs and Transformers on text from the CHILDES corpus and evaluate what they learn about English yes/no questions. |
| Outcome: | The proposed models perform well at capturing the surface statistics of child-directed speech, but generalize more consistent with an incorrect linear rule than the correct hierarchical rule. |
Do BabyLMs Wanna Learn Wanna Contraction? On the Learnability without Language-Specific Bias (2026.findings-acl)
Copied to clipboard
| Challenge: | grammatical constraints on wanna contraction can be learned by artificial learners under cognitively plausible learning conditions. |
| Approach: | They evaluate 24 BabyLMs from 2024 BabyLM Challenge and four standard models . they find that only encoder-based BabyLM models can capture wanna contraction . |
| Outcome: | The proposed models show modest but meaningful sensitivity on large datasets and high-frequency wanna instances. |