KonTra at CMCL 2021 Shared Task: Predicting Eye Movements by Combining BERT with Surface, Linguistic and Behavioral Information

Qi Yu, Aikaterini-Lida Kalouli, Diego Frassinelli

Abstract
This paper describes the submission of the team KonTra to the CMCL 2021 Shared Task on eye-tracking prediction. Our system combines the embeddings extracted from a fine-tuned BERT model with surface, linguistic and behavioral features, resulting in an average mean absolute error of 4.22 across all 5 eye-tracking measures. We show that word length and features representing the expectedness of a word are consistently the strongest predictors across all 5 eye-tracking measures.
Anthology ID:
2021.cmcl-1.15
Volume:
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
Month:
June
Year:
2021
Address:
Online
Venue:
CMCL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
120–124
Language:
URL:
https://aclanthology.org/2021.cmcl-1.15
DOI:
10.18653/v1/2021.cmcl-1.15
Bibkey:
Cite (ACL):
Qi Yu, Aikaterini-Lida Kalouli, and Diego Frassinelli. 2021. KonTra at CMCL 2021 Shared Task: Predicting Eye Movements by Combining BERT with Surface, Linguistic and Behavioral Information. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 120–124, Online. Association for Computational Linguistics.
Cite (Informal):
KonTra at CMCL 2021 Shared Task: Predicting Eye Movements by Combining BERT with Surface, Linguistic and Behavioral Information (Yu et al., CMCL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2021.cmcl-1.15.pdf
PDF Search