@inproceedings{sood-etal-2026-eyelignr,
title = "{EYELIGNR}: Aligning Gaze and Text via Contrastive Learning for Improved Reading Scanpath Prediction",
author = "Sood, Ekta and
Tannert, Simon and
Dhar, Prajit and
Sengupta, Meghdut and
Troiano, Enrica and
DMello, Sidney K.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1977/",
doi = "10.18653/2026.findings-emnlp.1977",
pages = "42147--42160",
ISBN = "979-8-89176-462-0",
abstract = "Modeling the interaction between gaze dynamics and linguistic structure remains a central challenge in scanpath prediction. Existing approaches either incorporate linguistic information in ways that do not fully respect the temporal progression of reading, or ignore linguistic structure altogether. Their effectiveness is further limited by the scarcity and heterogeneity of available eye-tracking data. To address these issues, we introduce EYELIGNR, a framework for spatiotemporal scanpath prediction that integrates linguistic information at the representation level. EYELIGNR conditions language representations on fixation order and aligns gaze and text within a shared embedding space through contrastive learning. Experiments on five reading corpora show that EYELIGNR generalizes effectively across reading conditions, improving over prior state of the art on multiple scanpath metrics (e.g., up to NLD {\textasciitilde}57{\%}, NLL {\textasciitilde}27{\%}, and FLA {\textasciitilde}59{\%})."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sood-etal-2026-eyelignr">
<titleInfo>
<title>EYELIGNR: Aligning Gaze and Text via Contrastive Learning for Improved Reading Scanpath Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekta</namePart>
<namePart type="family">Sood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Tannert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prajit</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghdut</namePart>
<namePart type="family">Sengupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrica</namePart>
<namePart type="family">Troiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sidney</namePart>
<namePart type="given">K</namePart>
<namePart type="family">DMello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Modeling the interaction between gaze dynamics and linguistic structure remains a central challenge in scanpath prediction. Existing approaches either incorporate linguistic information in ways that do not fully respect the temporal progression of reading, or ignore linguistic structure altogether. Their effectiveness is further limited by the scarcity and heterogeneity of available eye-tracking data. To address these issues, we introduce EYELIGNR, a framework for spatiotemporal scanpath prediction that integrates linguistic information at the representation level. EYELIGNR conditions language representations on fixation order and aligns gaze and text within a shared embedding space through contrastive learning. Experiments on five reading corpora show that EYELIGNR generalizes effectively across reading conditions, improving over prior state of the art on multiple scanpath metrics (e.g., up to NLD ~57%, NLL ~27%, and FLA ~59%).</abstract>
<identifier type="citekey">sood-etal-2026-eyelignr</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1977</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1977/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>42147</start>
<end>42160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EYELIGNR: Aligning Gaze and Text via Contrastive Learning for Improved Reading Scanpath Prediction
%A Sood, Ekta
%A Tannert, Simon
%A Dhar, Prajit
%A Sengupta, Meghdut
%A Troiano, Enrica
%A DMello, Sidney K.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F sood-etal-2026-eyelignr
%X Modeling the interaction between gaze dynamics and linguistic structure remains a central challenge in scanpath prediction. Existing approaches either incorporate linguistic information in ways that do not fully respect the temporal progression of reading, or ignore linguistic structure altogether. Their effectiveness is further limited by the scarcity and heterogeneity of available eye-tracking data. To address these issues, we introduce EYELIGNR, a framework for spatiotemporal scanpath prediction that integrates linguistic information at the representation level. EYELIGNR conditions language representations on fixation order and aligns gaze and text within a shared embedding space through contrastive learning. Experiments on five reading corpora show that EYELIGNR generalizes effectively across reading conditions, improving over prior state of the art on multiple scanpath metrics (e.g., up to NLD ~57%, NLL ~27%, and FLA ~59%).
%R 10.18653/2026.findings-emnlp.1977
%U https://aclanthology.org/2026.findings-emnlp.1977/
%U https://doi.org/10.18653/2026.findings-emnlp.1977
%P 42147-42160
Markdown (Informal)
[EYELIGNR: Aligning Gaze and Text via Contrastive Learning for Improved Reading Scanpath Prediction](https://aclanthology.org/2026.findings-emnlp.1977/) (Sood et al., Findings 2026)
ACL