Relating simple sentence representations in deep neural networks and the brain

Jat, S and Tang, H and Talukdar, P and Mitchel, T (2020) Relating simple sentence representations in deep neural networks and the brain. In: 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, 28 July-2 August 2019, Florence; Italy, pp. 5137-5154.

PDF ANN_MEE_ASS_COM_LIN_PRO_CON_5137-5154_2020.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

What is the relationship between sentence representations learned by deep recurrent models against those encoded by the brain? Is there any correspondence between hidden layers of these recurrent models and brain regions when processing sentences? Can these deep models be used to synthesize brain data which can then be utilized in other extrinsic tasks? We investigate these questions using sentences with simple syntax and semantics (e.g., The bone was eaten by the dog.). We consider multiple neural network architectures, including recently proposed ELMo and BERT. We use magnetoencephalography (MEG) brain recording data collected from human subjects when they were reading these simple sentences. Overall, we find that BERT's activations correlate the best with MEG brain data. We also find that the deep network representation can be used to generate brain data from new sentences to augment existing brain data. To the best of our knowledge, this is the first work showing that the MEG brain recording when reading a word in a sentence can be used to distinguish earlier words in the sentence. Our exploration is also the first to use deep neural network representations to generate synthetic brain data and to show that it helps in improving subsequent stimuli decoding task accuracy.

Item Type:	Conference Paper
Publication:	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher:	Association for Computational Linguistics (ACL)
Additional Information:	The copyright of this article belongs to Association for Computational Linguistics (ACL)
Keywords:	Brain; Brain mapping; Computational linguistics; Magnetoencephalography; Network architecture; Neural networks; Semantics, Brain data; Brain regions; Hidden layers; Human subjects; Multiple neural networks; Network representation; Recording data; Recurrent models, Deep neural networks
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	19 Oct 2020 10:33
Last Modified:	08 Dec 2022 10:13
URI:	https://eprints.iisc.ac.in/id/eprint/65443

Actions (login required)

View Item