Extending full text search for legal document collections using word embeddings

Jörg Landthaler, Bernhard Waltl, Patrick Holl, Florian Matthes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

20 Scopus citations

Abstract

Traditional full text search allows fast search for exact matches. However, full text search is not optimal to deal with synonyms or semantically related terms and phrases. In this paper we explore a novel method that provides the ability to find not only exact matches, but also semantically similar parts for arbitrary length search queries. We achieve this without the application of ontologies, but base our approach on Word Embeddings. Recently, Word Embeddings have been applied successfully for many natural language processing tasks. We argue that our method is well suited for legal document collections and examine its applicability for two different use cases: We conduct a case study on a stand-alone law, in particular the EU Data Protection Directive 94/46/EC (EU-DPD) in order to extract obligations. Secondly, from a collection of publicly available templates for German rental contracts we retrieve similar provisions.

Original languageEnglish
Title of host publicationLegal Knowledge and Information Systems - JURIX 2016
Subtitle of host publicationThe 29th Annual Conference
EditorsFloris Bex, Serena Villata
PublisherIOS Press BV
Pages73-82
Number of pages10
ISBN (Electronic)9781614997252
DOIs
StatePublished - 2016
Event29th International Conference on Legal Knowledge and Information Systems, JURIX 2016 - Nice, France
Duration: 14 Dec 201616 Dec 2016

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume294
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference29th International Conference on Legal Knowledge and Information Systems, JURIX 2016
Country/TerritoryFrance
CityNice
Period14/12/1616/12/16

Keywords

  • EU-DSGVO
  • Full text search
  • Information retrieval
  • Recommender systems
  • Relatedness search
  • Rental contracts
  • Text mining
  • Word embeddings

Fingerprint

Dive into the research topics of 'Extending full text search for legal document collections using word embeddings'. Together they form a unique fingerprint.

Cite this