@inproceedings{reich-etal-2024-reading-equal,
title = "Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations",
author = {Reich, David R. and
Deng, Shuwen and
Bj{\"o}rnsd{\'o}ttir, Marina and
J{\"a}ger, Lena and
Hollenstein, Nora},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1187",
pages = "13586--13594",
abstract = "Eye-tracking-while-reading corpora play a crucial role in the study of human language processing, and, more recently, have been leveraged for cognitively enhancing neural language models. A critical limitation of existing corpora is that they often lack diversity, comprising primarily native speakers. In this study, we expand the eye-tracking-while-reading dataset CopCo, which initially included only Danish L1 readers with and without dyslexia, by incorporating a new dataset of L2 readers with diverse L1 backgrounds. Thus, the extended CopCo corpus constitutes the first eye-tracking-while-reading dataset encompassing neurotypical L1 and L1 readers with dyslexia as well as L2 readers, all reading the same materials. We first provide extensive descriptive statistics of the extended CopCo corpus. Second, we investigate how different degrees of diversity of the training data affect a state-of-the-art generative model of eye movements in reading. Finally, we use this scanpath generation model for gaze-augmented language modeling and investigate the impact of diversity in the training data on the model{'}s performance on a range of NLP downstream tasks. The code can be found here: https://github.com/norahollenstein/copco-processing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reich-etal-2024-reading-equal">
<titleInfo>
<title>Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Reich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuwen</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Björnsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Jäger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Hollenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Eye-tracking-while-reading corpora play a crucial role in the study of human language processing, and, more recently, have been leveraged for cognitively enhancing neural language models. A critical limitation of existing corpora is that they often lack diversity, comprising primarily native speakers. In this study, we expand the eye-tracking-while-reading dataset CopCo, which initially included only Danish L1 readers with and without dyslexia, by incorporating a new dataset of L2 readers with diverse L1 backgrounds. Thus, the extended CopCo corpus constitutes the first eye-tracking-while-reading dataset encompassing neurotypical L1 and L1 readers with dyslexia as well as L2 readers, all reading the same materials. We first provide extensive descriptive statistics of the extended CopCo corpus. Second, we investigate how different degrees of diversity of the training data affect a state-of-the-art generative model of eye movements in reading. Finally, we use this scanpath generation model for gaze-augmented language modeling and investigate the impact of diversity in the training data on the model’s performance on a range of NLP downstream tasks. The code can be found here: https://github.com/norahollenstein/copco-processing.</abstract>
<identifier type="citekey">reich-etal-2024-reading-equal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1187</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13586</start>
<end>13594</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations
%A Reich, David R.
%A Deng, Shuwen
%A Björnsdóttir, Marina
%A Jäger, Lena
%A Hollenstein, Nora
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F reich-etal-2024-reading-equal
%X Eye-tracking-while-reading corpora play a crucial role in the study of human language processing, and, more recently, have been leveraged for cognitively enhancing neural language models. A critical limitation of existing corpora is that they often lack diversity, comprising primarily native speakers. In this study, we expand the eye-tracking-while-reading dataset CopCo, which initially included only Danish L1 readers with and without dyslexia, by incorporating a new dataset of L2 readers with diverse L1 backgrounds. Thus, the extended CopCo corpus constitutes the first eye-tracking-while-reading dataset encompassing neurotypical L1 and L1 readers with dyslexia as well as L2 readers, all reading the same materials. We first provide extensive descriptive statistics of the extended CopCo corpus. Second, we investigate how different degrees of diversity of the training data affect a state-of-the-art generative model of eye movements in reading. Finally, we use this scanpath generation model for gaze-augmented language modeling and investigate the impact of diversity in the training data on the model’s performance on a range of NLP downstream tasks. The code can be found here: https://github.com/norahollenstein/copco-processing.
%U https://aclanthology.org/2024.lrec-main.1187
%P 13586-13594
Markdown (Informal)
[Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations](https://aclanthology.org/2024.lrec-main.1187) (Reich et al., LREC-COLING 2024)
ACL