From Language to Language-ish: How Brain-Like is an LSTM’s Representation of Nonsensical Language Stimuli?

Maryam Hashemzadeh, Greta Kaufeld, Martha White, Andrea E. Martin, Alona Fyshe


Abstract
The representations generated by many models of language (word embeddings, recurrent neural networks and transformers) correlate to brain activity recorded while people read. However, these decoding results are usually based on the brain’s reaction to syntactically and semantically sound language stimuli. In this study, we asked: how does an LSTM (long short term memory) language model, trained (by and large) on semantically and syntactically intact language, represent a language sample with degraded semantic or syntactic information? Does the LSTM representation still resemble the brain’s reaction? We found that, even for some kinds of nonsensical language, there is a statistically significant relationship between the brain’s activity and the representations of an LSTM. This indicates that, at least in some instances, LSTMs and the human brain handle nonsensical data similarly.
Anthology ID:
2020.findings-emnlp.57
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
645–656
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.57
DOI:
10.18653/v1/2020.findings-emnlp.57
Bibkey:
Cite (ACL):
Maryam Hashemzadeh, Greta Kaufeld, Martha White, Andrea E. Martin, and Alona Fyshe. 2020. From Language to Language-ish: How Brain-Like is an LSTM’s Representation of Nonsensical Language Stimuli?. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 645–656, Online. Association for Computational Linguistics.
Cite (Informal):
From Language to Language-ish: How Brain-Like is an LSTM’s Representation of Nonsensical Language Stimuli? (Hashemzadeh et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.57.pdf