@inproceedings{meshgi-etal-2022-uncertainty,
title = "Uncertainty Regularized Multi-Task Learning",
author = "Meshgi, Kourosh and
Mirzaei, Maryam Sadat and
Sekine, Satoshi",
editor = "Barnes, Jeremy and
De Clercq, Orph{\'e}e and
Barriere, Valentin and
Tafreshi, Shabnam and
Alqahtani, Sawsan and
Sedoc, Jo{\~a}o and
Klinger, Roman and
Balahur, Alexandra",
booktitle = "Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment {\&} Social Media Analysis",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wassa-1.8",
doi = "10.18653/v1/2022.wassa-1.8",
pages = "78--88",
abstract = "By sharing parameters and providing task-independent shared features, multi-task deep neural networks are considered one of the most interesting ways for parallel learning from different tasks and domains. However, fine-tuning on one task may compromise the performance of other tasks or restrict the generalization of the shared learned features. To address this issue, we propose to use task uncertainty to gauge the effect of the shared feature changes on other tasks and prevent the model from overfitting or over-generalizing. We conducted an experiment on 16 text classification tasks, and findings showed that the proposed method consistently improves the performance of the baseline, facilitates the knowledge transfer of learned features to unseen data, and provides explicit control over the generalization of the shared model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meshgi-etal-2022-uncertainty">
<titleInfo>
<title>Uncertainty Regularized Multi-Task Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kourosh</namePart>
<namePart type="family">Meshgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Mirzaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sekine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sawsan</namePart>
<namePart type="family">Alqahtani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>By sharing parameters and providing task-independent shared features, multi-task deep neural networks are considered one of the most interesting ways for parallel learning from different tasks and domains. However, fine-tuning on one task may compromise the performance of other tasks or restrict the generalization of the shared learned features. To address this issue, we propose to use task uncertainty to gauge the effect of the shared feature changes on other tasks and prevent the model from overfitting or over-generalizing. We conducted an experiment on 16 text classification tasks, and findings showed that the proposed method consistently improves the performance of the baseline, facilitates the knowledge transfer of learned features to unseen data, and provides explicit control over the generalization of the shared model.</abstract>
<identifier type="citekey">meshgi-etal-2022-uncertainty</identifier>
<identifier type="doi">10.18653/v1/2022.wassa-1.8</identifier>
<location>
<url>https://aclanthology.org/2022.wassa-1.8</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>78</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty Regularized Multi-Task Learning
%A Meshgi, Kourosh
%A Mirzaei, Maryam Sadat
%A Sekine, Satoshi
%Y Barnes, Jeremy
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Alqahtani, Sawsan
%Y Sedoc, João
%Y Klinger, Roman
%Y Balahur, Alexandra
%S Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F meshgi-etal-2022-uncertainty
%X By sharing parameters and providing task-independent shared features, multi-task deep neural networks are considered one of the most interesting ways for parallel learning from different tasks and domains. However, fine-tuning on one task may compromise the performance of other tasks or restrict the generalization of the shared learned features. To address this issue, we propose to use task uncertainty to gauge the effect of the shared feature changes on other tasks and prevent the model from overfitting or over-generalizing. We conducted an experiment on 16 text classification tasks, and findings showed that the proposed method consistently improves the performance of the baseline, facilitates the knowledge transfer of learned features to unseen data, and provides explicit control over the generalization of the shared model.
%R 10.18653/v1/2022.wassa-1.8
%U https://aclanthology.org/2022.wassa-1.8
%U https://doi.org/10.18653/v1/2022.wassa-1.8
%P 78-88
Markdown (Informal)
[Uncertainty Regularized Multi-Task Learning](https://aclanthology.org/2022.wassa-1.8) (Meshgi et al., WASSA 2022)
ACL
- Kourosh Meshgi, Maryam Sadat Mirzaei, and Satoshi Sekine. 2022. Uncertainty Regularized Multi-Task Learning. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 78–88, Dublin, Ireland. Association for Computational Linguistics.