PIHKers at CMCL 2021 Shared Task: Cosine Similarity and Surprisal to Predict Human Reading Patterns.

Lavinia Salicchi, Alessandro Lenci


Abstract
Eye-tracking psycholinguistic studies have revealed that context-word semantic coherence and predictability influence language processing. In this paper we show our approach to predict eye-tracking features from the ZuCo dataset for the shared task of the Cognitive Modeling and Computational Linguistics (CMCL2021) workshop. Using both cosine similarity and surprisal within a regression model, we significantly improved the baseline Mean Absolute Error computed among five eye-tracking features.
Anthology ID:
2021.cmcl-1.12
Volume:
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
Month:
June
Year:
2021
Address:
Online
Venues:
CMCL | NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
102–107
Language:
URL:
https://aclanthology.org/2021.cmcl-1.12
DOI:
10.18653/v1/2021.cmcl-1.12
Bibkey:
Cite (ACL):
Lavinia Salicchi and Alessandro Lenci. 2021. PIHKers at CMCL 2021 Shared Task: Cosine Similarity and Surprisal to Predict Human Reading Patterns.. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 102–107, Online. Association for Computational Linguistics.
Cite (Informal):
PIHKers at CMCL 2021 Shared Task: Cosine Similarity and Surprisal to Predict Human Reading Patterns. (Salicchi & Lenci, CMCL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.cmcl-1.12.pdf