Modeling Fixation Behavior in Reading with Character-level Neural Attention

Songpeng Yan, Michael Hahn, Frank Keller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Humans read text in a sequence of fixations connected by saccades spanning 7–9 characters. While most words are fixated, some are skipped, and sometimes there are reverse saccades. Previous work has explained this behavior in terms of a tradeoff between the accuracy of text comprehension and the efficiency of reading, and modeled this using attention-based neural networks. We extend this line of work by modeling the locations of individual fixations down to the character level. We evaluate our model on an eye-tracking corpus and demonstrate that it reproduces human reading patterns, both quantitatively and qualitatively. It achieves good performance in predicting fixation positions and also captures lexical effects on fixation rate and landing position effects.
Original languageEnglish
Title of host publicationProceedings of the 44th Annual Conference of the Cognitive Science Society
EditorsJennifer Culbertson, Andrew Perfors, Hugh Rabagliati, Veronica Ramenzoni
PublisherCognitive Science Society
Pages2171-2177
Number of pages7
Volume44
Publication statusPublished - 17 Jun 2022
Event44th Annual Meeting of the Cognitive Science Society - Toronto, Canada
Duration: 27 Jul 202230 Jul 2022
Conference number: 44
https://cognitivesciencesociety.org/cogsci-2022/

Publication series

NameProceedings of the Annual Meeting of the Cognitive Science Society
PublisherCognitive Science Society
Volume44
ISSN (Electronic)1069-7977

Conference

Conference44th Annual Meeting of the Cognitive Science Society
Abbreviated titleCogSci 2022
Country/TerritoryCanada
CityToronto
Period27/07/2230/07/22
Internet address

Keywords

  • Computational linguistics
  • eye-tracking and reading
  • Cognitive modeling

Fingerprint

Dive into the research topics of 'Modeling Fixation Behavior in Reading with Character-level Neural Attention'. Together they form a unique fingerprint.

Cite this