@inproceedings{yang-etal-2023-task,
title = "Task-specific Compression for Multi-task Language Models using Attribution-based Pruning",
author = "Yang, Nakyeong and
Jang, Yunah and
Lee, Hwanhee and
Jeong, Seohyeong and
Jung, Kyomin",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.43",
doi = "10.18653/v1/2023.findings-eacl.43",
pages = "594--604",
abstract = "Multi-task language models show outstanding performance for various natural language understanding tasks with only a single model. However, these language models inevitably utilize an unnecessarily large number of model parameters, even when used only for a specific task. In this paper, we propose a novel training-free compression method for multi-task language models using pruning method. Specifically, we use an attribution method to determine which neurons are essential for performing a specific task. We task-specifically prune unimportant neurons and leave only task-specific parameters. Furthermore, we extend our method to be applicable in both low-resource and unsupervised settings. Since our compression method is training-free, it uses little computing resources and does not update the pre-trained parameters of language models, reducing storage space usage. Experimental results on the six widely-used datasets show that our proposed pruning method significantly outperforms baseline pruning methods. In addition, we demonstrate that our method preserves performance even in an unseen domain setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2023-task">
<titleInfo>
<title>Task-specific Compression for Multi-task Language Models using Attribution-based Pruning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nakyeong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunah</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwanhee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seohyeong</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyomin</namePart>
<namePart type="family">Jung</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>Findings of the Association for Computational Linguistics: EACL 2023</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>Multi-task language models show outstanding performance for various natural language understanding tasks with only a single model. However, these language models inevitably utilize an unnecessarily large number of model parameters, even when used only for a specific task. In this paper, we propose a novel training-free compression method for multi-task language models using pruning method. Specifically, we use an attribution method to determine which neurons are essential for performing a specific task. We task-specifically prune unimportant neurons and leave only task-specific parameters. Furthermore, we extend our method to be applicable in both low-resource and unsupervised settings. Since our compression method is training-free, it uses little computing resources and does not update the pre-trained parameters of language models, reducing storage space usage. Experimental results on the six widely-used datasets show that our proposed pruning method significantly outperforms baseline pruning methods. In addition, we demonstrate that our method preserves performance even in an unseen domain setting.</abstract>
<identifier type="citekey">yang-etal-2023-task</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.43</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.43</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>594</start>
<end>604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Task-specific Compression for Multi-task Language Models using Attribution-based Pruning
%A Yang, Nakyeong
%A Jang, Yunah
%A Lee, Hwanhee
%A Jeong, Seohyeong
%A Jung, Kyomin
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F yang-etal-2023-task
%X Multi-task language models show outstanding performance for various natural language understanding tasks with only a single model. However, these language models inevitably utilize an unnecessarily large number of model parameters, even when used only for a specific task. In this paper, we propose a novel training-free compression method for multi-task language models using pruning method. Specifically, we use an attribution method to determine which neurons are essential for performing a specific task. We task-specifically prune unimportant neurons and leave only task-specific parameters. Furthermore, we extend our method to be applicable in both low-resource and unsupervised settings. Since our compression method is training-free, it uses little computing resources and does not update the pre-trained parameters of language models, reducing storage space usage. Experimental results on the six widely-used datasets show that our proposed pruning method significantly outperforms baseline pruning methods. In addition, we demonstrate that our method preserves performance even in an unseen domain setting.
%R 10.18653/v1/2023.findings-eacl.43
%U https://aclanthology.org/2023.findings-eacl.43
%U https://doi.org/10.18653/v1/2023.findings-eacl.43
%P 594-604
Markdown (Informal)
[Task-specific Compression for Multi-task Language Models using Attribution-based Pruning](https://aclanthology.org/2023.findings-eacl.43) (Yang et al., Findings 2023)
ACL