HkAmsters at CMCL 2022 Shared Task: Predicting Eye-Tracking Data from a Gradient Boosting Framework with Linguistic Features

Lavinia Salicchi, Rong Xiang, Yu-yin Hsu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Eye movement data are used in psycholinguistic studies to infer information regarding cognitive processes during reading. In this paper, we describe our proposed method for the Shared Task of Cognitive Modeling and Computational Linguistics (CMCL) 2022 - Subtask 1, which involves data from multiple datasets on 6 languages. We compared different regression models using features of the target word and its previous word, and target word surprisal as regression features. Our final system, using a gradient boosting regressor, achieved the lowest mean absolute error (MAE), resulting in the best system of the competition.
Original languageEnglish
Title of host publicationProceedings of the Workshop on Cognitive Modeling and Computational Linguistics
EditorsEmmanuele Chersoni, Nora Hollenstein, Cassandra Jacobs, Yohei Oseki, Laurent Prévot, Enrico Santus
Pages114–120
DOIs
Publication statusPublished - Mar 2022
EventWorkshop on Cognitive Modeling and Computational Linguistics (CMCL) 2022 - Dublin, Ireland
Duration: 26 Apr 202226 Apr 2022
https://cmclorg.github.io/

Competition

CompetitionWorkshop on Cognitive Modeling and Computational Linguistics (CMCL) 2022
Country/TerritoryIreland
CityDublin
Period26/04/2226/04/22
Internet address

Keywords

  • gradient boosting
  • eyetracking
  • prediction
  • linguistic features
  • crosslingual

Fingerprint

Dive into the research topics of 'HkAmsters at CMCL 2022 Shared Task: Predicting Eye-Tracking Data from a Gradient Boosting Framework with Linguistic Features'. Together they form a unique fingerprint.

Cite this