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

Q1 Decision Sciences

Annals of Data Science Pub Date : 2022-09-06 DOI:10.1007/s40745-022-00442-4

Ambedkar Kanapala, Sukomal Pal, Suresh Dara, Srikanth Jannu

引用次数: 0

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.

Abstract Image

查看原文本刊更多论文

应用信息检索方法检索法律领域相关文章

检索法律文本是建立法律领域问题解答系统的一个重要步骤，该系统需要相关文章来回答查询。在法律信息检索方面已经开展了大量研究。然而，检索问题的相关文章是一项极具挑战性的任务。在本文中，我们介绍了一种新颖的方法来检索与律师资格考试问题相关的民法文章。我们在 Terrier 中使用了三种模型 Hiemstra、BM25 和 PL2F。我们的系统根据指定的模型从文档集中检索排名靠前的文档，并为每个查询输出一份文档。根据投票算法选出最佳模型。然后，利用文档配对标识和文章之间的映射，检索出适当的民法文章。该系统在训练数据上获得了超过 71.16% 的民法文章正确率，在测试数据上获得了中等分数。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Annals of Data Science Decision Sciences-Statistics, Probability and Uncertainty

CiteScore

6.50

自引率

0.00%

发文量

期刊介绍： Annals of Data Science (ADS) publishes cutting-edge research findings, experimental results and case studies of data science. Although Data Science is regarded as an interdisciplinary field of using mathematics, statistics, databases, data mining, high-performance computing, knowledge management and virtualization to discover knowledge from Big Data, it should have its own scientific contents, such as axioms, laws and rules, which are fundamentally important for experts in different fields to explore their own interests from Big Data. ADS encourages contributors to address such challenging problems at this exchange platform. At present, how to discover knowledge from heterogeneous data under Big Data environment needs to be addressed. ADS is a series of volumes edited by either the editorial office or guest editors. Guest editors will be responsible for call-for-papers and the review process for high-quality contributions in their volumes.