@inproceedings{niklaus-etal-2021-swiss,
title = "{S}wiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark",
author = {Niklaus, Joel and
Chalkidis, Ilias and
St{\"u}rmer, Matthias},
editor = "Aletras, Nikolaos and
Androutsopoulos, Ion and
Barrett, Leslie and
Goanta, Catalina and
Preotiuc-Pietro, Daniel",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nllp-1.3/",
doi = "10.18653/v1/2021.nllp-1.3",
pages = "19--35",
abstract = "In many jurisdictions, the excessive workload of courts leads to high delays. Suitable predictive AI models can assist legal professionals in their work, and thus enhance and speed up the process. So far, Legal Judgment Prediction (LJP) datasets have been released in English, French, and Chinese. We publicly release a multilingual (German, French, and Italian), diachronic (2000-2020) corpus of 85K cases from the Federal Supreme Court of Switzer- land (FSCS). We evaluate state-of-the-art BERT-based methods including two variants of BERT that overcome the BERT input (text) length limitation (up to 512 tokens). Hierarchical BERT has the best performance (approx. 68-70{\%} Macro-F1-Score in German and French). Furthermore, we study how several factors (canton of origin, year of publication, text length, legal area) affect performance. We release both the benchmark dataset and our code to accelerate future research and ensure reproducibility."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niklaus-etal-2021-swiss">
<titleInfo>
<title>Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Niklaus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Stürmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2021</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">Ion</namePart>
<namePart type="family">Androutsopoulos</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">Catalina</namePart>
<namePart type="family">Goanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preotiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In many jurisdictions, the excessive workload of courts leads to high delays. Suitable predictive AI models can assist legal professionals in their work, and thus enhance and speed up the process. So far, Legal Judgment Prediction (LJP) datasets have been released in English, French, and Chinese. We publicly release a multilingual (German, French, and Italian), diachronic (2000-2020) corpus of 85K cases from the Federal Supreme Court of Switzer- land (FSCS). We evaluate state-of-the-art BERT-based methods including two variants of BERT that overcome the BERT input (text) length limitation (up to 512 tokens). Hierarchical BERT has the best performance (approx. 68-70% Macro-F1-Score in German and French). Furthermore, we study how several factors (canton of origin, year of publication, text length, legal area) affect performance. We release both the benchmark dataset and our code to accelerate future research and ensure reproducibility.</abstract>
<identifier type="citekey">niklaus-etal-2021-swiss</identifier>
<identifier type="doi">10.18653/v1/2021.nllp-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.nllp-1.3/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>19</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark
%A Niklaus, Joel
%A Chalkidis, Ilias
%A Stürmer, Matthias
%Y Aletras, Nikolaos
%Y Androutsopoulos, Ion
%Y Barrett, Leslie
%Y Goanta, Catalina
%Y Preotiuc-Pietro, Daniel
%S Proceedings of the Natural Legal Language Processing Workshop 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F niklaus-etal-2021-swiss
%X In many jurisdictions, the excessive workload of courts leads to high delays. Suitable predictive AI models can assist legal professionals in their work, and thus enhance and speed up the process. So far, Legal Judgment Prediction (LJP) datasets have been released in English, French, and Chinese. We publicly release a multilingual (German, French, and Italian), diachronic (2000-2020) corpus of 85K cases from the Federal Supreme Court of Switzer- land (FSCS). We evaluate state-of-the-art BERT-based methods including two variants of BERT that overcome the BERT input (text) length limitation (up to 512 tokens). Hierarchical BERT has the best performance (approx. 68-70% Macro-F1-Score in German and French). Furthermore, we study how several factors (canton of origin, year of publication, text length, legal area) affect performance. We release both the benchmark dataset and our code to accelerate future research and ensure reproducibility.
%R 10.18653/v1/2021.nllp-1.3
%U https://aclanthology.org/2021.nllp-1.3/
%U https://doi.org/10.18653/v1/2021.nllp-1.3
%P 19-35
Markdown (Informal)
[Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark](https://aclanthology.org/2021.nllp-1.3/) (Niklaus et al., NLLP 2021)
ACL