@inproceedings{miyazaki-etal-2022-cross,
title = "Cross-domain Analysis on {J}apanese Legal Pretrained Language Models",
author = "Miyazaki, Keisuke and
Yamada, Hiroaki and
Tokunaga, Takenobu",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.26/",
doi = "10.18653/v1/2022.findings-aacl.26",
pages = "274--281",
abstract = "This paper investigates the pretrained language model (PLM) specialised in the Japanese legal domain. We create PLMs using different pretraining strategies and investigate their performance across multiple domains. Our findings are (i) the PLM built with general domain data can be improved by further pretraining with domain-specific data, (ii) domain-specific PLMs can learn domain-specific and general word meanings simultaneously and can distinguish them, (iii) domain-specific PLMs work better on its target domain; still, the PLMs retain the information learnt in the original PLM even after being further pretrained with domain-specific data, (iv) the PLMs sequentially pretrained with corpora of different domains show high performance for the later learnt domains."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miyazaki-etal-2022-cross">
<titleInfo>
<title>Cross-domain Analysis on Japanese Legal Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keisuke</namePart>
<namePart type="family">Miyazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takenobu</namePart>
<namePart type="family">Tokunaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the pretrained language model (PLM) specialised in the Japanese legal domain. We create PLMs using different pretraining strategies and investigate their performance across multiple domains. Our findings are (i) the PLM built with general domain data can be improved by further pretraining with domain-specific data, (ii) domain-specific PLMs can learn domain-specific and general word meanings simultaneously and can distinguish them, (iii) domain-specific PLMs work better on its target domain; still, the PLMs retain the information learnt in the original PLM even after being further pretrained with domain-specific data, (iv) the PLMs sequentially pretrained with corpora of different domains show high performance for the later learnt domains.</abstract>
<identifier type="citekey">miyazaki-etal-2022-cross</identifier>
<identifier type="doi">10.18653/v1/2022.findings-aacl.26</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.26/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>274</start>
<end>281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-domain Analysis on Japanese Legal Pretrained Language Models
%A Miyazaki, Keisuke
%A Yamada, Hiroaki
%A Tokunaga, Takenobu
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F miyazaki-etal-2022-cross
%X This paper investigates the pretrained language model (PLM) specialised in the Japanese legal domain. We create PLMs using different pretraining strategies and investigate their performance across multiple domains. Our findings are (i) the PLM built with general domain data can be improved by further pretraining with domain-specific data, (ii) domain-specific PLMs can learn domain-specific and general word meanings simultaneously and can distinguish them, (iii) domain-specific PLMs work better on its target domain; still, the PLMs retain the information learnt in the original PLM even after being further pretrained with domain-specific data, (iv) the PLMs sequentially pretrained with corpora of different domains show high performance for the later learnt domains.
%R 10.18653/v1/2022.findings-aacl.26
%U https://aclanthology.org/2022.findings-aacl.26/
%U https://doi.org/10.18653/v1/2022.findings-aacl.26
%P 274-281
Markdown (Informal)
[Cross-domain Analysis on Japanese Legal Pretrained Language Models](https://aclanthology.org/2022.findings-aacl.26/) (Miyazaki et al., Findings 2022)
ACL