@inproceedings{ab80bbdb88fd431f80b72c31d0139985,
title = "Extending full text search for legal document collections using word embeddings",
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.",
keywords = "EU-DSGVO, Full text search, Information retrieval, Recommender systems, Relatedness search, Rental contracts, Text mining, Word embeddings",
author = "J{\"o}rg Landthaler and Bernhard Waltl and Patrick Holl and Florian Matthes",
note = "Publisher Copyright: {\textcopyright} 2016 The authors and IOS Press. All rights reserved.; 29th International Conference on Legal Knowledge and Information Systems, JURIX 2016 ; Conference date: 14-12-2016 Through 16-12-2016",
year = "2016",
doi = "10.3233/978-1-61499-726-9-73",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press BV",
pages = "73--82",
editor = "Floris Bex and Serena Villata",
booktitle = "Legal Knowledge and Information Systems - JURIX 2016",
}