[CaCL] CaCL reading for 3/30

[Clark, Christian]

Hi CaCL members,

Our reading for next Thursday will be McCoy et al. 2023.

Title: How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech

Link: https://arxiv.org/abs/2301.11462

Abstract:
When acquiring syntax, children consistently choose hierarchical rules over competing non-hierarchical possibilities. Is this preference due to a learning bias for hierarchical structure, or due to more general biases that interact with hierarchical cues in children's linguistic input? We explore these possibilities by training LSTMs and Transformers - two types of neural networks without a hierarchical bias - on data similar in quantity and content to children's linguistic input: text from the CHILDES corpus. We then evaluate what these models have learned about English yes/no questions, a phenomenon for which hierarchical structure is crucial. We find that, though they perform well at capturing the surface statistics of child-directed speech (as measured by perplexity), both model types generalize in a way more consistent with an incorrect linear rule than the correct hierarchical rule. These results suggest that human-like generalization from text alone requires stronger biases than the general sequence-processing biases of standard neural network architectures.

----
Christian Clark
Ph.D. Student
Department of Linguistics
The Ohio State University
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/cacl/attachments/20230323/a6b5be3f/attachment.html>