File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Book Chapter: Judgment Tagging and Recommendation Using Pre-Trained Language Models and Legal Taxonomy

TitleJudgment Tagging and Recommendation Using Pre-Trained Language Models and Legal Taxonomy
Authors
Keywordsjudgment recommendation
judgment tagging
keyword extraction
Issue Date5-Dec-2022
PublisherIOS Press
Abstract

We study the problem of machine comprehension of court judgments and generation of descriptive tags for judgments. Our approach makes use of a legal taxonomy D, which serves as a dictionary of canonicalized legal concepts. Given a court judgment J, our method identifies the key contents of J and then applies Word2Vec and BERT-based models to select a short list TJ of terms/phrases from the taxonomy D as descriptive tags of J. The tag set TJ suggests concepts that are relevant to or associative with J and provides a simple mechanism for readers of J to compose associative queries for effective judgment recommendation. Our prototype system implemented on the Hong Kong Legal Information Institute (HKLII) platform shows that our method provides a highly effective tool that assists users in exploring a judgment corpus and in obtaining relevant judgment recommendation.


Persistent Identifierhttp://hdl.handle.net/10722/337186
ISBN
ISSN
2023 SCImago Journal Rankings: 0.281

 

DC FieldValueLanguage
dc.contributor.authorWu, Tien-Hsuan-
dc.contributor.authorKao, Ben-
dc.contributor.authorChan, Henry-
dc.contributor.authorCheung, Michael MK-
dc.date.accessioned2024-03-11T10:18:46Z-
dc.date.available2024-03-11T10:18:46Z-
dc.date.issued2022-12-05-
dc.identifier.isbn9781643683645-
dc.identifier.issn0922-6389-
dc.identifier.urihttp://hdl.handle.net/10722/337186-
dc.description.abstract<p>We study the problem of machine comprehension of court judgments and generation of descriptive tags for judgments. Our approach makes use of a legal taxonomy D, which serves as a dictionary of canonicalized legal concepts. Given a court judgment J, our method identifies the key contents of J and then applies Word2Vec and BERT-based models to select a short list T<sub>J</sub> of terms/phrases from the taxonomy D as descriptive tags of J. The tag set T<sub>J</sub> suggests concepts that are relevant to or associative with J and provides a simple mechanism for readers of J to compose associative queries for effective judgment recommendation. Our prototype system implemented on the Hong Kong Legal Information Institute (HKLII) platform shows that our method provides a highly effective tool that assists users in exploring a judgment corpus and in obtaining relevant judgment recommendation.<br></p>-
dc.languageeng-
dc.publisherIOS Press-
dc.relation.ispartofThe 21st European Conference on Artificial Intelligence (ECAI), August, 2014, Czech Republic-
dc.subjectjudgment recommendation-
dc.subjectjudgment tagging-
dc.subjectkeyword extraction-
dc.titleJudgment Tagging and Recommendation Using Pre-Trained Language Models and Legal Taxonomy-
dc.typeBook_Chapter-
dc.identifier.doi10.3233/FAIA220476-
dc.identifier.scopuseid_2-s2.0-85146715101-
dc.identifier.volume362-
dc.identifier.spage255-
dc.identifier.epage260-
dc.identifier.eisbn9781643683652-
dc.identifier.issnl0922-6389-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats