@inproceedings{cheng-etal-2022-snapshot,
title = "Snapshot-Guided Domain Adaptation for {ELECTRA}",
author = "Cheng, Daixuan and
Huang, Shaohan and
Liu, Jianfeng and
Zhan, Yuefeng and
Sun, Hao and
Wei, Furu and
Deng, Denvy and
Zhang, Qi",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.163",
doi = "10.18653/v1/2022.findings-emnlp.163",
pages = "2226--2232",
abstract = "Discriminative pre-trained language models, such as ELECTRA, have achieved promising performances in a variety of general tasks. However, these generic pre-trained models struggle to capture domain-specific knowledge of domain-related tasks. In this work, we propose a novel domain-adaptation method for ELECTRA, which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters. We show that by re-weighting the losses of domain-specific tokens, ELECTRA can be effectively adapted to different domains. The experimental results in both computer science and biomedical domains show that the proposed method can achieve state-of-the-art results on the domain-related tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2022-snapshot">
<titleInfo>
<title>Snapshot-Guided Domain Adaptation for ELECTRA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daixuan</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaohan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuefeng</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denvy</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Discriminative pre-trained language models, such as ELECTRA, have achieved promising performances in a variety of general tasks. However, these generic pre-trained models struggle to capture domain-specific knowledge of domain-related tasks. In this work, we propose a novel domain-adaptation method for ELECTRA, which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters. We show that by re-weighting the losses of domain-specific tokens, ELECTRA can be effectively adapted to different domains. The experimental results in both computer science and biomedical domains show that the proposed method can achieve state-of-the-art results on the domain-related tasks.</abstract>
<identifier type="citekey">cheng-etal-2022-snapshot</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.163</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.163</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2226</start>
<end>2232</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Snapshot-Guided Domain Adaptation for ELECTRA
%A Cheng, Daixuan
%A Huang, Shaohan
%A Liu, Jianfeng
%A Zhan, Yuefeng
%A Sun, Hao
%A Wei, Furu
%A Deng, Denvy
%A Zhang, Qi
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F cheng-etal-2022-snapshot
%X Discriminative pre-trained language models, such as ELECTRA, have achieved promising performances in a variety of general tasks. However, these generic pre-trained models struggle to capture domain-specific knowledge of domain-related tasks. In this work, we propose a novel domain-adaptation method for ELECTRA, which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters. We show that by re-weighting the losses of domain-specific tokens, ELECTRA can be effectively adapted to different domains. The experimental results in both computer science and biomedical domains show that the proposed method can achieve state-of-the-art results on the domain-related tasks.
%R 10.18653/v1/2022.findings-emnlp.163
%U https://aclanthology.org/2022.findings-emnlp.163
%U https://doi.org/10.18653/v1/2022.findings-emnlp.163
%P 2226-2232
Markdown (Informal)
[Snapshot-Guided Domain Adaptation for ELECTRA](https://aclanthology.org/2022.findings-emnlp.163) (Cheng et al., Findings 2022)
ACL
- Daixuan Cheng, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Furu Wei, Denvy Deng, and Qi Zhang. 2022. Snapshot-Guided Domain Adaptation for ELECTRA. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2226–2232, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.