@inproceedings{tuteja-gonzalez-jucla-2023-long,
title = "Long Text Classification using Transformers with Paragraph Selection Strategies",
author = "Tuteja, Mohit and
Gonz{\'a}lez Jucl{\`a}, Daniel",
editor = "Preoțiuc-Pietro, Daniel and
Goanta, Catalina and
Chalkidis, Ilias and
Barrett, Leslie and
Spanakis, Gerasimos and
Aletras, Nikolaos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nllp-1.3/",
doi = "10.18653/v1/2023.nllp-1.3",
pages = "17--24",
abstract = "In the legal domain, we often perform classification tasks on very long documents, for example court judgements. These documents often contain thousands of words, so the length of these documents poses a challenge for this modelling task. In this research paper, we present a comprehensive evaluation of various strategies to perform long text classification using Transformers in conjunction with strategies to select document chunks using traditional NLP models. We conduct our experiments on 6 benchmark datasets comprising lengthy documents, 4 of which are publicly available. Each dataset has a median word count exceeding 1,000. Our evaluation encompasses state-of-the-art Transformer models, such as RoBERTa, Longformer, HAT, MEGA and LegalBERT and compares them with a traditional baseline TF-IDF + Neural Network (NN) model. We investigate the effectiveness of pre-training on large corpora, fine tuning strategies, and transfer learning techniques in the context of long text classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tuteja-gonzalez-jucla-2023-long">
<titleInfo>
<title>Long Text Classification using Transformers with Paragraph Selection Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Tuteja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">González Juclà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoțiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catalina</namePart>
<namePart type="family">Goanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the legal domain, we often perform classification tasks on very long documents, for example court judgements. These documents often contain thousands of words, so the length of these documents poses a challenge for this modelling task. In this research paper, we present a comprehensive evaluation of various strategies to perform long text classification using Transformers in conjunction with strategies to select document chunks using traditional NLP models. We conduct our experiments on 6 benchmark datasets comprising lengthy documents, 4 of which are publicly available. Each dataset has a median word count exceeding 1,000. Our evaluation encompasses state-of-the-art Transformer models, such as RoBERTa, Longformer, HAT, MEGA and LegalBERT and compares them with a traditional baseline TF-IDF + Neural Network (NN) model. We investigate the effectiveness of pre-training on large corpora, fine tuning strategies, and transfer learning techniques in the context of long text classification.</abstract>
<identifier type="citekey">tuteja-gonzalez-jucla-2023-long</identifier>
<identifier type="doi">10.18653/v1/2023.nllp-1.3</identifier>
<location>
<url>https://aclanthology.org/2023.nllp-1.3/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>17</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Long Text Classification using Transformers with Paragraph Selection Strategies
%A Tuteja, Mohit
%A González Juclà, Daniel
%Y Preoțiuc-Pietro, Daniel
%Y Goanta, Catalina
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Spanakis, Gerasimos
%Y Aletras, Nikolaos
%S Proceedings of the Natural Legal Language Processing Workshop 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F tuteja-gonzalez-jucla-2023-long
%X In the legal domain, we often perform classification tasks on very long documents, for example court judgements. These documents often contain thousands of words, so the length of these documents poses a challenge for this modelling task. In this research paper, we present a comprehensive evaluation of various strategies to perform long text classification using Transformers in conjunction with strategies to select document chunks using traditional NLP models. We conduct our experiments on 6 benchmark datasets comprising lengthy documents, 4 of which are publicly available. Each dataset has a median word count exceeding 1,000. Our evaluation encompasses state-of-the-art Transformer models, such as RoBERTa, Longformer, HAT, MEGA and LegalBERT and compares them with a traditional baseline TF-IDF + Neural Network (NN) model. We investigate the effectiveness of pre-training on large corpora, fine tuning strategies, and transfer learning techniques in the context of long text classification.
%R 10.18653/v1/2023.nllp-1.3
%U https://aclanthology.org/2023.nllp-1.3/
%U https://doi.org/10.18653/v1/2023.nllp-1.3
%P 17-24
Markdown (Informal)
[Long Text Classification using Transformers with Paragraph Selection Strategies](https://aclanthology.org/2023.nllp-1.3/) (Tuteja & González Juclà, NLLP 2023)
ACL