Evaluating Neural Language Models as Cognitive Models of Language Acquisition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911547510489088 |
|---|---|
| author | Martínez, Héctor Javier Vázquez Heuser, Annika Lea Yang, Charles Kodner, Jordan |
| author_facet | Martínez, Héctor Javier Vázquez Heuser, Annika Lea Yang, Charles Kodner, Jordan |
| contents | The success of neural language models (LMs) on many technological tasks has brought about their potential relevance as scientific theories of language despite some clear differences between LM training and child language acquisition. In this paper we argue that some of the most prominent benchmarks for evaluating the syntactic capacities of LMs may not be sufficiently rigorous. In particular, we show that the template-based benchmarks lack the structural diversity commonly found in the theoretical and psychological studies of language. When trained on small-scale data modeling child language acquisition, the LMs can be readily matched by simple baseline models. We advocate for the use of the readily available, carefully curated datasets that have been evaluated for gradient acceptability by large pools of native speakers and are designed to probe the structural basis of grammar specifically. On one such dataset, the LI-Adger dataset, LMs evaluate sentences in a way inconsistent with human language users. We conclude with suggestions for better connecting LMs with the empirical study of child language acquisition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_20093 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Evaluating Neural Language Models as Cognitive Models of Language Acquisition Martínez, Héctor Javier Vázquez Heuser, Annika Lea Yang, Charles Kodner, Jordan Computation and Language Artificial Intelligence The success of neural language models (LMs) on many technological tasks has brought about their potential relevance as scientific theories of language despite some clear differences between LM training and child language acquisition. In this paper we argue that some of the most prominent benchmarks for evaluating the syntactic capacities of LMs may not be sufficiently rigorous. In particular, we show that the template-based benchmarks lack the structural diversity commonly found in the theoretical and psychological studies of language. When trained on small-scale data modeling child language acquisition, the LMs can be readily matched by simple baseline models. We advocate for the use of the readily available, carefully curated datasets that have been evaluated for gradient acceptability by large pools of native speakers and are designed to probe the structural basis of grammar specifically. On one such dataset, the LI-Adger dataset, LMs evaluate sentences in a way inconsistent with human language users. We conclude with suggestions for better connecting LMs with the empirical study of child language acquisition. |
| title | Evaluating Neural Language Models as Cognitive Models of Language Acquisition |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2310.20093 |