Salvato in:
Dettagli Bibliografici
Autori principali: Beauchemin, David, Albert-Rochette, Michelle, Khoury, Richard, Déziel, Pierre-Luc
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.16870
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916913460805632
author Beauchemin, David
Albert-Rochette, Michelle
Khoury, Richard
Déziel, Pierre-Luc
author_facet Beauchemin, David
Albert-Rochette, Michelle
Khoury, Richard
Déziel, Pierre-Luc
contents Simplifying text while preserving its meaning is a complex yet essential task, especially in sensitive domain applications like legal texts. When applied to a specialized field, like the legal domain, preservation differs significantly from its role in regular texts. This paper introduces FrJUDGE, a new dataset to assess legal meaning preservation between two legal texts. It also introduces JUDGEBERT, a novel evaluation metric designed to assess legal meaning preservation in French legal text simplification. JUDGEBERT demonstrates a superior correlation with human judgment compared to existing metrics. It also passes two crucial sanity checks, while other metrics did not: For two identical sentences, it always returns a score of 100%; on the other hand, it returns 0% for two unrelated sentences. Our findings highlight its potential to transform legal NLP applications, ensuring accuracy and accessibility for text simplification for legal practitioners and lay users.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16870
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences
Beauchemin, David
Albert-Rochette, Michelle
Khoury, Richard
Déziel, Pierre-Luc
Computation and Language
Simplifying text while preserving its meaning is a complex yet essential task, especially in sensitive domain applications like legal texts. When applied to a specialized field, like the legal domain, preservation differs significantly from its role in regular texts. This paper introduces FrJUDGE, a new dataset to assess legal meaning preservation between two legal texts. It also introduces JUDGEBERT, a novel evaluation metric designed to assess legal meaning preservation in French legal text simplification. JUDGEBERT demonstrates a superior correlation with human judgment compared to existing metrics. It also passes two crucial sanity checks, while other metrics did not: For two identical sentences, it always returns a score of 100%; on the other hand, it returns 0% for two unrelated sentences. Our findings highlight its potential to transform legal NLP applications, ensuring accuracy and accessibility for text simplification for legal practitioners and lay users.
title JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences
topic Computation and Language
url https://arxiv.org/abs/2508.16870