@inproceedings{xiao-etal-2024-fine-grained,
title = "Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training",
author = "Xiao, Chaojun and
Sun, Yutao and
Yao, Yuan and
Han, Xu and
Zhang, Wenbin and
Liu, Zhiyuan and
Sun, Maosong",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.644",
pages = "7324--7335",
abstract = "Legal Argument-Pair Extraction (LAE) is dedicated to the identification of interactive arguments targeting the same subject matter within legal complaints and corresponding defenses. This process serves as a foundation for automatically recognizing the focal points of disputes. Current methodologies predominantly conceptualize LAE as a supervised sentence-pair classification problem and usually necessitate extensive manual annotations, thereby constraining their scalability and general applicability. To this end, we present an innovative approach to LAE that focuses on fine-grained alignment of argument pairs, building upon coarse-grained complaint-defense pairs. This strategy stems from two key observations: 1) In general, every argument presented in a legal complaint is likely to be addressed by at least one corresponding argument in the defense. 2) It{'}s rare for multiple complaint arguments to be addressed by a single defense argument; rather, each complaint argument usually corresponds to a unique defense argument. Motivated by these insights, we develop a specialized pre-training framework. Our model employs pre-training objectives designed to exploit the coarse-grained supervision signals. This enables expressive representations of legal arguments for LAE, even when working with a limited amount of labeled data. To verify the effectiveness of our model, we construct the largest LAE datasets from two representative causes, private lending, and contract dispute. The experimental results demonstrate that our model can effectively capture informative argument knowledge from unlabeled complaint-defense pairs and outperform the unsupervised and supervised baselines by 3.7 and 2.4 points on average respectively. Besides, our model can reach superior accuracy with only half manually annotated data. The datasets and code can be found in https://github.com/thunlp/LAE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2024-fine-grained">
<titleInfo>
<title>Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaojun</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Legal Argument-Pair Extraction (LAE) is dedicated to the identification of interactive arguments targeting the same subject matter within legal complaints and corresponding defenses. This process serves as a foundation for automatically recognizing the focal points of disputes. Current methodologies predominantly conceptualize LAE as a supervised sentence-pair classification problem and usually necessitate extensive manual annotations, thereby constraining their scalability and general applicability. To this end, we present an innovative approach to LAE that focuses on fine-grained alignment of argument pairs, building upon coarse-grained complaint-defense pairs. This strategy stems from two key observations: 1) In general, every argument presented in a legal complaint is likely to be addressed by at least one corresponding argument in the defense. 2) It’s rare for multiple complaint arguments to be addressed by a single defense argument; rather, each complaint argument usually corresponds to a unique defense argument. Motivated by these insights, we develop a specialized pre-training framework. Our model employs pre-training objectives designed to exploit the coarse-grained supervision signals. This enables expressive representations of legal arguments for LAE, even when working with a limited amount of labeled data. To verify the effectiveness of our model, we construct the largest LAE datasets from two representative causes, private lending, and contract dispute. The experimental results demonstrate that our model can effectively capture informative argument knowledge from unlabeled complaint-defense pairs and outperform the unsupervised and supervised baselines by 3.7 and 2.4 points on average respectively. Besides, our model can reach superior accuracy with only half manually annotated data. The datasets and code can be found in https://github.com/thunlp/LAE.</abstract>
<identifier type="citekey">xiao-etal-2024-fine-grained</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.644</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7324</start>
<end>7335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training
%A Xiao, Chaojun
%A Sun, Yutao
%A Yao, Yuan
%A Han, Xu
%A Zhang, Wenbin
%A Liu, Zhiyuan
%A Sun, Maosong
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F xiao-etal-2024-fine-grained
%X Legal Argument-Pair Extraction (LAE) is dedicated to the identification of interactive arguments targeting the same subject matter within legal complaints and corresponding defenses. This process serves as a foundation for automatically recognizing the focal points of disputes. Current methodologies predominantly conceptualize LAE as a supervised sentence-pair classification problem and usually necessitate extensive manual annotations, thereby constraining their scalability and general applicability. To this end, we present an innovative approach to LAE that focuses on fine-grained alignment of argument pairs, building upon coarse-grained complaint-defense pairs. This strategy stems from two key observations: 1) In general, every argument presented in a legal complaint is likely to be addressed by at least one corresponding argument in the defense. 2) It’s rare for multiple complaint arguments to be addressed by a single defense argument; rather, each complaint argument usually corresponds to a unique defense argument. Motivated by these insights, we develop a specialized pre-training framework. Our model employs pre-training objectives designed to exploit the coarse-grained supervision signals. This enables expressive representations of legal arguments for LAE, even when working with a limited amount of labeled data. To verify the effectiveness of our model, we construct the largest LAE datasets from two representative causes, private lending, and contract dispute. The experimental results demonstrate that our model can effectively capture informative argument knowledge from unlabeled complaint-defense pairs and outperform the unsupervised and supervised baselines by 3.7 and 2.4 points on average respectively. Besides, our model can reach superior accuracy with only half manually annotated data. The datasets and code can be found in https://github.com/thunlp/LAE.
%U https://aclanthology.org/2024.lrec-main.644
%P 7324-7335
Markdown (Informal)
[Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training](https://aclanthology.org/2024.lrec-main.644) (Xiao et al., LREC-COLING 2024)
ACL
- Chaojun Xiao, Yutao Sun, Yuan Yao, Xu Han, Wenbin Zhang, Zhiyuan Liu, and Maosong Sun. 2024. Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7324–7335, Torino, Italia. ELRA and ICCL.