@inproceedings{khurana-etal-2023-synthesizing,
title = "Synthesizing Human Gaze Feedback for Improved {NLP} Performance",
author = "Khurana, Varun and
Kumar, Yaman and
Hollenstein, Nora and
Kumar, Rajesh and
Krishnamurthy, Balaji",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.139/",
doi = "10.18653/v1/2023.eacl-main.139",
pages = "1895--1908",
abstract = "Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training language models) or implicit (e.g. using human cognitive signals in the form of eyetracking). Prior eye tracking and NLP research reveal that cognitive processes, such as human scanpaths, gleaned from human gaze patterns aid in the understanding and performance of NLP models. However, the collection of real eyetracking data for NLP tasks is challenging due to the requirement of expensive and precise equipment coupled with privacy invasion issues. To address this challenge, we propose ScanTextGAN, a novel model for generating human scanpaths over text. We show that ScanTextGAN-generated scanpaths can approximate meaningful cognitive signals in human gaze patterns. We include synthetically generated scanpaths in four popular NLP tasks spanning six different datasets as proof of concept and show that the models augmented with generated scanpaths improve the performance of all downstream NLP tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khurana-etal-2023-synthesizing">
<titleInfo>
<title>Synthesizing Human Gaze Feedback for Improved NLP Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Khurana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaman</namePart>
<namePart type="family">Kumar</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>
<name type="personal">
<namePart type="given">Rajesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balaji</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training language models) or implicit (e.g. using human cognitive signals in the form of eyetracking). Prior eye tracking and NLP research reveal that cognitive processes, such as human scanpaths, gleaned from human gaze patterns aid in the understanding and performance of NLP models. However, the collection of real eyetracking data for NLP tasks is challenging due to the requirement of expensive and precise equipment coupled with privacy invasion issues. To address this challenge, we propose ScanTextGAN, a novel model for generating human scanpaths over text. We show that ScanTextGAN-generated scanpaths can approximate meaningful cognitive signals in human gaze patterns. We include synthetically generated scanpaths in four popular NLP tasks spanning six different datasets as proof of concept and show that the models augmented with generated scanpaths improve the performance of all downstream NLP tasks.</abstract>
<identifier type="citekey">khurana-etal-2023-synthesizing</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.139</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.139/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1895</start>
<end>1908</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthesizing Human Gaze Feedback for Improved NLP Performance
%A Khurana, Varun
%A Kumar, Yaman
%A Hollenstein, Nora
%A Kumar, Rajesh
%A Krishnamurthy, Balaji
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F khurana-etal-2023-synthesizing
%X Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training language models) or implicit (e.g. using human cognitive signals in the form of eyetracking). Prior eye tracking and NLP research reveal that cognitive processes, such as human scanpaths, gleaned from human gaze patterns aid in the understanding and performance of NLP models. However, the collection of real eyetracking data for NLP tasks is challenging due to the requirement of expensive and precise equipment coupled with privacy invasion issues. To address this challenge, we propose ScanTextGAN, a novel model for generating human scanpaths over text. We show that ScanTextGAN-generated scanpaths can approximate meaningful cognitive signals in human gaze patterns. We include synthetically generated scanpaths in four popular NLP tasks spanning six different datasets as proof of concept and show that the models augmented with generated scanpaths improve the performance of all downstream NLP tasks.
%R 10.18653/v1/2023.eacl-main.139
%U https://aclanthology.org/2023.eacl-main.139/
%U https://doi.org/10.18653/v1/2023.eacl-main.139
%P 1895-1908
Markdown (Informal)
[Synthesizing Human Gaze Feedback for Improved NLP Performance](https://aclanthology.org/2023.eacl-main.139/) (Khurana et al., EACL 2023)
ACL
- Varun Khurana, Yaman Kumar, Nora Hollenstein, Rajesh Kumar, and Balaji Krishnamurthy. 2023. Synthesizing Human Gaze Feedback for Improved NLP Performance. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1895–1908, Dubrovnik, Croatia. Association for Computational Linguistics.