CDRNN: Discovering Complex Dynamics in Human Language Processing

Cory Shain


Abstract
The human mind is a dynamical system, yet many analysis techniques used to study it are limited in their ability to capture the complex dynamics that may characterize mental processes. This study proposes the continuous-time deconvolutional regressive neural network (CDRNN), a deep neural extension of continuous-time deconvolutional regression (Shain & Schuler, 2021) that jointly captures time-varying, non-linear, and delayed influences of predictors (e.g. word surprisal) on the response (e.g. reading time). Despite this flexibility, CDRNN is interpretable and able to illuminate patterns in human cognition that are otherwise difficult to study. Behavioral and fMRI experiments reveal detailed and plausible estimates of human language processing dynamics that generalize better than CDR and other baselines, supporting a potential role for CDRNN in studying human language processing.
Anthology ID:
2021.acl-long.288
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3718–3734
Language:
URL:
https://aclanthology.org/2021.acl-long.288
DOI:
10.18653/v1/2021.acl-long.288
Bibkey:
Cite (ACL):
Cory Shain. 2021. CDRNN: Discovering Complex Dynamics in Human Language Processing. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3718–3734, Online. Association for Computational Linguistics.
Cite (Informal):
CDRNN: Discovering Complex Dynamics in Human Language Processing (Shain, ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.288.pdf
Video:
 https://aclanthology.org/2021.acl-long.288.mp4
Code
 coryshain/cdr
Data
Natural Stories