Discourse structure interacts with reference but not syntax in neural language models

Forrest Davis, Marten van Schijndel


Abstract
Language models (LMs) trained on large quantities of text have been claimed to acquire abstract linguistic representations. Our work tests the robustness of these abstractions by focusing on the ability of LMs to learn interactions between different linguistic representations. In particular, we utilized stimuli from psycholinguistic studies showing that humans can condition reference (i.e. coreference resolution) and syntactic processing on the same discourse structure (implicit causality). We compared both transformer and long short-term memory LMs to find that, contrary to humans, implicit causality only influences LM behavior for reference, not syntax, despite model representations that encode the necessary discourse information. Our results further suggest that LM behavior can contradict not only learned representations of discourse but also syntactic agreement, pointing to shortcomings of standard language modeling.
Anthology ID:
2020.conll-1.32
Volume:
Proceedings of the 24th Conference on Computational Natural Language Learning
Month:
November
Year:
2020
Address:
Online
Editors:
Raquel Fernández, Tal Linzen
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
396–407
Language:
URL:
https://aclanthology.org/2020.conll-1.32
DOI:
10.18653/v1/2020.conll-1.32
Bibkey:
Cite (ACL):
Forrest Davis and Marten van Schijndel. 2020. Discourse structure interacts with reference but not syntax in neural language models. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 396–407, Online. Association for Computational Linguistics.
Cite (Informal):
Discourse structure interacts with reference but not syntax in neural language models (Davis & van Schijndel, CoNLL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.conll-1.32.pdf
Optional supplementary material:
 2020.conll-1.32.OptionalSupplementaryMaterial.pdf
Code
 forrestdavis/ImplicitCausality