Building a Production-Ready Multi-Label Classifier for Legal Documents with Digital-Twin-Distiller
Open Access
- 29 January 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1470
Abstract
One of the most time-consuming parts of an attorney’s job is finding similar legal cases. Categorization of legal documents by their subject matter can significantly increase the discoverability of digitalized court decisions. This is a multi-label classification problem, where each relatively long text can fit into more than one legal category. The proposed paper shows a solution where this multi-label classification problem is decomposed into more than a hundred binary classification problems. Several approaches have been tested, including different machine-learning and text-augmentation techniques to produce a practically applicable model. The proposed models and the methodologies were encapsulated and deployed as a digital-twin into a production environment. The performance of the created machine learning-based application reaches and could also improve the human-experts performance on this monotonous and labor-intensive task. It could increase the e-discoverability of the documents by about 50%.Keywords
Funding Information
- Nemzeti Kutatási és Technológiai Hivatal (Project No. 2020-1.1.2-PIACI-KFI-2020-00049)
This publication has 38 references indexed in Scilit:
- Text summarization from legal documents: a surveyArtificial Intelligence Review, 2017
- A general approach for predicting the behavior of the Supreme Court of the United StatesPLOS ONE, 2017
- Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspectivePeerJ Computer Science, 2016
- Software Architecture for Document AnonymizationElectronic Notes in Theoretical Computer Science, 2015
- ANOVA–principal component analysis and ANOVA–simultaneous component analysis: a comparisonJournal of Chemometrics, 2011
- Document categorization in legal electronic discovery: computer classification vs. manual reviewJournal of the American Society for Information Science and Technology, 2009
- Learning multi-label scene classificationPattern Recognition, 2004
- An Evaluation of Statistical Approaches to Text CategorizationInformation Retrieval Journal, 1999
- Analysis of variance (ANOVA)Chemometrics and Intelligent Laboratory Systems, 1989
- A STATISTICAL INTERPRETATION OF TERM SPECIFICITY AND ITS APPLICATION IN RETRIEVALJournal of Documentation, 1972