@inproceedings{belfathi-etal-2025-simple,
title = "A Simple but Effective Context Retrieval for Sequential Sentence Classification in Long Legal Documents",
author = "Belfathi, Anas and
Hernandez, Nicolas and
Laura, Monceaux and
Dufour, Richard",
editor = "Chistova, Elena and
Cimiano, Philipp and
Haddadan, Shohreh and
Lapesa, Gabriella and
Ruiz-Dolz, Ramon",
booktitle = "Proceedings of the 12th Argument mining Workshop",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.argmining-1.15/",
doi = "10.18653/v1/2025.argmining-1.15",
pages = "160--167",
ISBN = "979-8-89176-258-9",
abstract = "Sequential sentence classification extends traditional classification, especially useful when dealing with long documents. However, state-of-the-art approaches face two major challenges: pre-trained language models struggle with input-length constraints, while proposed hierarchical models often introduce irrelevant content. To address these limitations, we propose a simple and effective document-level retrieval approach that extracts only the most relevant context. Specifically, we introduce two heuristic strategies: \textbf{Sequential}, which captures local information, and \textbf{Selective}, which retrieves the semantically similar sentences. Experiments on legal domain datasets show that both heuristics lead to consistent improvements over the baseline, with an average increase of ${\sim}5.5$ weighted-F1 points. Sequential heuristics outperform hierarchical models on two out of three datasets, with gains of up to ${\sim}1.5$, demonstrating the benefits of targeted context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belfathi-etal-2025-simple">
<titleInfo>
<title>A Simple but Effective Context Retrieval for Sequential Sentence Classification in Long Legal Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anas</namePart>
<namePart type="family">Belfathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monceaux</namePart>
<namePart type="family">Laura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Dufour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Argument mining Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Chistova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Cimiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohreh</namePart>
<namePart type="family">Haddadan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Ruiz-Dolz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-258-9</identifier>
</relatedItem>
<abstract>Sequential sentence classification extends traditional classification, especially useful when dealing with long documents. However, state-of-the-art approaches face two major challenges: pre-trained language models struggle with input-length constraints, while proposed hierarchical models often introduce irrelevant content. To address these limitations, we propose a simple and effective document-level retrieval approach that extracts only the most relevant context. Specifically, we introduce two heuristic strategies: Sequential, which captures local information, and Selective, which retrieves the semantically similar sentences. Experiments on legal domain datasets show that both heuristics lead to consistent improvements over the baseline, with an average increase of \sim5.5 weighted-F1 points. Sequential heuristics outperform hierarchical models on two out of three datasets, with gains of up to \sim1.5, demonstrating the benefits of targeted context.</abstract>
<identifier type="citekey">belfathi-etal-2025-simple</identifier>
<identifier type="doi">10.18653/v1/2025.argmining-1.15</identifier>
<location>
<url>https://aclanthology.org/2025.argmining-1.15/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>160</start>
<end>167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple but Effective Context Retrieval for Sequential Sentence Classification in Long Legal Documents
%A Belfathi, Anas
%A Hernandez, Nicolas
%A Laura, Monceaux
%A Dufour, Richard
%Y Chistova, Elena
%Y Cimiano, Philipp
%Y Haddadan, Shohreh
%Y Lapesa, Gabriella
%Y Ruiz-Dolz, Ramon
%S Proceedings of the 12th Argument mining Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-258-9
%F belfathi-etal-2025-simple
%X Sequential sentence classification extends traditional classification, especially useful when dealing with long documents. However, state-of-the-art approaches face two major challenges: pre-trained language models struggle with input-length constraints, while proposed hierarchical models often introduce irrelevant content. To address these limitations, we propose a simple and effective document-level retrieval approach that extracts only the most relevant context. Specifically, we introduce two heuristic strategies: Sequential, which captures local information, and Selective, which retrieves the semantically similar sentences. Experiments on legal domain datasets show that both heuristics lead to consistent improvements over the baseline, with an average increase of \sim5.5 weighted-F1 points. Sequential heuristics outperform hierarchical models on two out of three datasets, with gains of up to \sim1.5, demonstrating the benefits of targeted context.
%R 10.18653/v1/2025.argmining-1.15
%U https://aclanthology.org/2025.argmining-1.15/
%U https://doi.org/10.18653/v1/2025.argmining-1.15
%P 160-167
Markdown (Informal)
[A Simple but Effective Context Retrieval for Sequential Sentence Classification in Long Legal Documents](https://aclanthology.org/2025.argmining-1.15/) (Belfathi et al., ArgMining 2025)
ACL