Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations

Ethan Wilcox, Roger Levy, Richard Futrell


Abstract
Work using artificial languages as training input has shown that LSTMs are capable of inducing the stack-like data structures required to represent context-free and certain mildly context-sensitive languages — formal language classes which correspond in theory to the hierarchical structures of natural language. Here we present a suite of experiments probing whether neural language models trained on linguistic data induce these stack-like data structures and deploy them while incrementally predicting words. We study two natural language phenomena: center embedding sentences and syntactic island constraints on the filler–gap dependency. In order to properly predict words in these structures, a model must be able to temporarily suppress certain expectations and then recover those expectations later, essentially pushing and popping these expectations on a stack. Our results provide evidence that models can successfully suppress and recover expectations in many cases, but do not fully recover their previous grammatical state.
Anthology ID:
W19-4819
Volume:
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Tal Linzen, Grzegorz Chrupała, Yonatan Belinkov, Dieuwke Hupkes
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
181–190
Language:
URL:
https://aclanthology.org/W19-4819
DOI:
10.18653/v1/W19-4819
Bibkey:
Cite (ACL):
Ethan Wilcox, Roger Levy, and Richard Futrell. 2019. Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 181–190, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations (Wilcox et al., BlackboxNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4819.pdf
Data
Billion Word Benchmark