@inproceedings{he-etal-2021-effectiveness,
title = "On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation",
author = "He, Ruidan and
Liu, Linlin and
Ye, Hai and
Tan, Qingyu and
Ding, Bosheng and
Cheng, Liying and
Low, Jiawei and
Bing, Lidong and
Si, Luo",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.172",
doi = "10.18653/v1/2021.acl-long.172",
pages = "2208--2222",
abstract = "Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to fine-tuning. However, existing work only focuses on the parameter-efficient aspect of adapter-based tuning while lacking further investigation on its effectiveness. In this paper, we study the latter. We first show that adapter-based tuning better mitigates forgetting issues than fine-tuning since it yields representations with less deviation from those generated by the initial PrLM. We then empirically compare the two tuning methods on several downstream NLP tasks and settings. We demonstrate that 1) adapter-based tuning outperforms fine-tuning on low-resource and cross-lingual tasks; 2) it is more robust to overfitting and less sensitive to changes in learning rates.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2021-effectiveness">
<titleInfo>
<title>On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruidan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyu</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bosheng</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liying</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Low</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidong</namePart>
<namePart type="family">Bing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luo</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to fine-tuning. However, existing work only focuses on the parameter-efficient aspect of adapter-based tuning while lacking further investigation on its effectiveness. In this paper, we study the latter. We first show that adapter-based tuning better mitigates forgetting issues than fine-tuning since it yields representations with less deviation from those generated by the initial PrLM. We then empirically compare the two tuning methods on several downstream NLP tasks and settings. We demonstrate that 1) adapter-based tuning outperforms fine-tuning on low-resource and cross-lingual tasks; 2) it is more robust to overfitting and less sensitive to changes in learning rates.</abstract>
<identifier type="citekey">he-etal-2021-effectiveness</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.172</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.172</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2208</start>
<end>2222</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation
%A He, Ruidan
%A Liu, Linlin
%A Ye, Hai
%A Tan, Qingyu
%A Ding, Bosheng
%A Cheng, Liying
%A Low, Jiawei
%A Bing, Lidong
%A Si, Luo
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F he-etal-2021-effectiveness
%X Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to fine-tuning. However, existing work only focuses on the parameter-efficient aspect of adapter-based tuning while lacking further investigation on its effectiveness. In this paper, we study the latter. We first show that adapter-based tuning better mitigates forgetting issues than fine-tuning since it yields representations with less deviation from those generated by the initial PrLM. We then empirically compare the two tuning methods on several downstream NLP tasks and settings. We demonstrate that 1) adapter-based tuning outperforms fine-tuning on low-resource and cross-lingual tasks; 2) it is more robust to overfitting and less sensitive to changes in learning rates.
%R 10.18653/v1/2021.acl-long.172
%U https://aclanthology.org/2021.acl-long.172
%U https://doi.org/10.18653/v1/2021.acl-long.172
%P 2208-2222
Markdown (Informal)
[On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation](https://aclanthology.org/2021.acl-long.172) (He et al., ACL-IJCNLP 2021)
ACL
- Ruidan He, Linlin Liu, Hai Ye, Qingyu Tan, Bosheng Ding, Liying Cheng, Jiawei Low, Lidong Bing, and Luo Si. 2021. On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2208–2222, Online. Association for Computational Linguistics.