Applying an Information Retrieval Approach to Retrieve Relevant Articles in the Legal Domain

Abstract

Retrieving legal texts is an important step for building a question answering system on law domain, which needs relevant articles to answer a query. Remarkable research has been done on legal information retrieval. However, retrieving relevant articles for a question is an extremely challenging task. In this paper, we describe a novel approach to retrieve relevant civil law article for a question from legal bar exams. We used three models Hiemstra, BM25 and PL2F implemented within Terrier. Our system retrieves top-ranked document from the collection according to the models specified and it outputs one single document per query. The best model has been selected on the basis of voting algorithm. Appropriate civil law articles are then retrieved using a mapping between document pair-id and the articles. The system achieved an accuracy of over 71.16% of correct civil law articles on training data and moderate scores on test data. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.