@inproceedings{schraagen-etal-2022-abstractive,
title = "Abstractive Summarization of {D}utch Court Verdicts Using Sequence-to-sequence Models",
author = {Schraagen, Marijn and
Bex, Floris and
Van De Luijtgaarden, Nick and
Prijs, Dani{\"e}l},
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nllp-1.7",
doi = "10.18653/v1/2022.nllp-1.7",
pages = "76--87",
abstract = "With the legal sector embracing digitization, the increasing availability of information has led to a need for systems that can automatically summarize legal documents. Most existing research on legal text summarization has so far focused on extractive models, which can result in awkward summaries, as sentences in legal documents can be very long and detailed. In this study, we apply two abstractive summarization models on a Dutch legal domain dataset. The results show that existing models transfer quite well across domains and languages: the ROUGE scores of our experiments are comparable to state-of-the-art studies on English news article texts. Examining one of the models showed the capability of rewriting long legal sentences to much shorter ones, using mostly vocabulary from the source document. Human evaluation shows that for both models hand-made summaries are still perceived as more relevant and readable, and automatic summaries do not always capture elements such as background, considerations and judgement. Still, generated summaries are valuable if only a keyword summary or no summary at all is present.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schraagen-etal-2022-abstractive">
<titleInfo>
<title>Abstractive Summarization of Dutch Court Verdicts Using Sequence-to-sequence Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marijn</namePart>
<namePart type="family">Schraagen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Floris</namePart>
<namePart type="family">Bex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nick</namePart>
<namePart type="family">Van De Luijtgaarden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniël</namePart>
<namePart type="family">Prijs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</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">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the legal sector embracing digitization, the increasing availability of information has led to a need for systems that can automatically summarize legal documents. Most existing research on legal text summarization has so far focused on extractive models, which can result in awkward summaries, as sentences in legal documents can be very long and detailed. In this study, we apply two abstractive summarization models on a Dutch legal domain dataset. The results show that existing models transfer quite well across domains and languages: the ROUGE scores of our experiments are comparable to state-of-the-art studies on English news article texts. Examining one of the models showed the capability of rewriting long legal sentences to much shorter ones, using mostly vocabulary from the source document. Human evaluation shows that for both models hand-made summaries are still perceived as more relevant and readable, and automatic summaries do not always capture elements such as background, considerations and judgement. Still, generated summaries are valuable if only a keyword summary or no summary at all is present.</abstract>
<identifier type="citekey">schraagen-etal-2022-abstractive</identifier>
<identifier type="doi">10.18653/v1/2022.nllp-1.7</identifier>
<location>
<url>https://aclanthology.org/2022.nllp-1.7</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>76</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Abstractive Summarization of Dutch Court Verdicts Using Sequence-to-sequence Models
%A Schraagen, Marijn
%A Bex, Floris
%A Van De Luijtgaarden, Nick
%A Prijs, Daniël
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%S Proceedings of the Natural Legal Language Processing Workshop 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F schraagen-etal-2022-abstractive
%X With the legal sector embracing digitization, the increasing availability of information has led to a need for systems that can automatically summarize legal documents. Most existing research on legal text summarization has so far focused on extractive models, which can result in awkward summaries, as sentences in legal documents can be very long and detailed. In this study, we apply two abstractive summarization models on a Dutch legal domain dataset. The results show that existing models transfer quite well across domains and languages: the ROUGE scores of our experiments are comparable to state-of-the-art studies on English news article texts. Examining one of the models showed the capability of rewriting long legal sentences to much shorter ones, using mostly vocabulary from the source document. Human evaluation shows that for both models hand-made summaries are still perceived as more relevant and readable, and automatic summaries do not always capture elements such as background, considerations and judgement. Still, generated summaries are valuable if only a keyword summary or no summary at all is present.
%R 10.18653/v1/2022.nllp-1.7
%U https://aclanthology.org/2022.nllp-1.7
%U https://doi.org/10.18653/v1/2022.nllp-1.7
%P 76-87
Markdown (Informal)
[Abstractive Summarization of Dutch Court Verdicts Using Sequence-to-sequence Models](https://aclanthology.org/2022.nllp-1.7) (Schraagen et al., NLLP 2022)
ACL