@inproceedings{deng-etal-2024-fine,
title = "Fine-Tuning Pre-Trained Language Models with Gaze Supervision",
author = {Deng, Shuwen and
Prasse, Paul and
Reich, David and
Scheffer, Tobias and
J{\"a}ger, Lena},
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-short.21",
doi = "10.18653/v1/2024.acl-short.21",
pages = "217--224",
abstract = "Human gaze data provide cognitive information that reflect human language comprehension and has been effectively integrated into a variety of natural language processing (NLP) tasks, demonstrating improved performance over corresponding plain text-based models. In this work, we propose to integrate a gaze module into pre-trained language models (LMs) at the fine-tuning stage to improve their capabilities to learn representations that are grounded in human language processing. This is done by extending the conventional purely text-based fine-tuning objective with an auxiliary loss to exploit cognitive signals. The gaze module is only included during training, retaining compatibility with existing pre-trained LM-based pipelines. We evaluate the proposed approach using two distinct pre-trained LMs on the GLUE benchmark and observe that the proposed model improves performance compared to both standard fine-tuning and traditional text augmentation baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2024-fine">
<titleInfo>
<title>Fine-Tuning Pre-Trained Language Models with Gaze Supervision</title>
</titleInfo>
<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">Paul</namePart>
<namePart type="family">Prasse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Reich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Scheffer</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>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human gaze data provide cognitive information that reflect human language comprehension and has been effectively integrated into a variety of natural language processing (NLP) tasks, demonstrating improved performance over corresponding plain text-based models. In this work, we propose to integrate a gaze module into pre-trained language models (LMs) at the fine-tuning stage to improve their capabilities to learn representations that are grounded in human language processing. This is done by extending the conventional purely text-based fine-tuning objective with an auxiliary loss to exploit cognitive signals. The gaze module is only included during training, retaining compatibility with existing pre-trained LM-based pipelines. We evaluate the proposed approach using two distinct pre-trained LMs on the GLUE benchmark and observe that the proposed model improves performance compared to both standard fine-tuning and traditional text augmentation baselines.</abstract>
<identifier type="citekey">deng-etal-2024-fine</identifier>
<identifier type="doi">10.18653/v1/2024.acl-short.21</identifier>
<location>
<url>https://aclanthology.org/2024.acl-short.21</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>217</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Tuning Pre-Trained Language Models with Gaze Supervision
%A Deng, Shuwen
%A Prasse, Paul
%A Reich, David
%A Scheffer, Tobias
%A Jäger, Lena
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F deng-etal-2024-fine
%X Human gaze data provide cognitive information that reflect human language comprehension and has been effectively integrated into a variety of natural language processing (NLP) tasks, demonstrating improved performance over corresponding plain text-based models. In this work, we propose to integrate a gaze module into pre-trained language models (LMs) at the fine-tuning stage to improve their capabilities to learn representations that are grounded in human language processing. This is done by extending the conventional purely text-based fine-tuning objective with an auxiliary loss to exploit cognitive signals. The gaze module is only included during training, retaining compatibility with existing pre-trained LM-based pipelines. We evaluate the proposed approach using two distinct pre-trained LMs on the GLUE benchmark and observe that the proposed model improves performance compared to both standard fine-tuning and traditional text augmentation baselines.
%R 10.18653/v1/2024.acl-short.21
%U https://aclanthology.org/2024.acl-short.21
%U https://doi.org/10.18653/v1/2024.acl-short.21
%P 217-224
Markdown (Informal)
[Fine-Tuning Pre-Trained Language Models with Gaze Supervision](https://aclanthology.org/2024.acl-short.21) (Deng et al., ACL 2024)
ACL
- Shuwen Deng, Paul Prasse, David Reich, Tobias Scheffer, and Lena Jäger. 2024. Fine-Tuning Pre-Trained Language Models with Gaze Supervision. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 217–224, Bangkok, Thailand. Association for Computational Linguistics.