@inproceedings{huo-etal-2023-antcontenttech,
title = "{A}nt{C}ontent{T}ech at {S}em{E}val-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding {I}ndian Legal Texts",
author = "Huo, Jingjing and
Zhang, Kezun and
Liu, Zhengyong and
Lin, Xuan and
Xu, Wenqiang and
Zheng, Maozong and
Wang, Zhaoguo and
Li, Song",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.54",
doi = "10.18653/v1/2023.semeval-1.54",
pages = "402--408",
abstract = "The objective of this shared task is to gain an understanding of legal texts, and it is beset with difficulties such as the comprehension of lengthy noisy legal documents, domain specificity as well as the scarcity of annotated data. To address these challenges, we propose a system that employs a hierarchical model and integrates domain-adaptive pretraining, data augmentation, and auxiliary-task learning techniques. Moreover, to enhance generalization and robustness, we ensemble the models that utilize these diverse techniques. Our system ranked first on the RR sub-task and in the middle for the other two sub-tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huo-etal-2023-antcontenttech">
<titleInfo>
<title>AntContentTech at SemEval-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding Indian Legal Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingjing</namePart>
<namePart type="family">Huo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kezun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqiang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maozong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoguo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The objective of this shared task is to gain an understanding of legal texts, and it is beset with difficulties such as the comprehension of lengthy noisy legal documents, domain specificity as well as the scarcity of annotated data. To address these challenges, we propose a system that employs a hierarchical model and integrates domain-adaptive pretraining, data augmentation, and auxiliary-task learning techniques. Moreover, to enhance generalization and robustness, we ensemble the models that utilize these diverse techniques. Our system ranked first on the RR sub-task and in the middle for the other two sub-tasks.</abstract>
<identifier type="citekey">huo-etal-2023-antcontenttech</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.54</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.54</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>402</start>
<end>408</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AntContentTech at SemEval-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding Indian Legal Texts
%A Huo, Jingjing
%A Zhang, Kezun
%A Liu, Zhengyong
%A Lin, Xuan
%A Xu, Wenqiang
%A Zheng, Maozong
%A Wang, Zhaoguo
%A Li, Song
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F huo-etal-2023-antcontenttech
%X The objective of this shared task is to gain an understanding of legal texts, and it is beset with difficulties such as the comprehension of lengthy noisy legal documents, domain specificity as well as the scarcity of annotated data. To address these challenges, we propose a system that employs a hierarchical model and integrates domain-adaptive pretraining, data augmentation, and auxiliary-task learning techniques. Moreover, to enhance generalization and robustness, we ensemble the models that utilize these diverse techniques. Our system ranked first on the RR sub-task and in the middle for the other two sub-tasks.
%R 10.18653/v1/2023.semeval-1.54
%U https://aclanthology.org/2023.semeval-1.54
%U https://doi.org/10.18653/v1/2023.semeval-1.54
%P 402-408
Markdown (Informal)
[AntContentTech at SemEval-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding Indian Legal Texts](https://aclanthology.org/2023.semeval-1.54) (Huo et al., SemEval 2023)
ACL
- Jingjing Huo, Kezun Zhang, Zhengyong Liu, Xuan Lin, Wenqiang Xu, Maozong Zheng, Zhaoguo Wang, and Song Li. 2023. AntContentTech at SemEval-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding Indian Legal Texts. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 402–408, Toronto, Canada. Association for Computational Linguistics.