Joint Reference and Relation Extraction from Legal Documents with Enhanced Decoder Input
Open Access
- 1 June 2023
- journal article
- research article
- Published by Walter de Gruyter GmbH in Cybernetics and Information Technologies
- Vol. 23 (2) , 72-86
Abstract
This paper deals with an important task in legal text processing, namely reference and relation extraction from legal documents, which includes two subtasks: 1) reference extraction; 2) relation determination. Motivated by the fact that two subtasks are related and share common information, we propose a joint learning model that solves simultaneously both subtasks. Our model employs a Transformer-based encoder-decoder architecture with non-autoregressive decoding that allows relaxing the sequentiality of traditional seq2seq models and extracting references and relations in one inference step. We also propose a method to enrich the decoder input with learnable meaningful information and therefore, improve the model accuracy. Experimental results on a dataset consisting of 5031 legal documents in Vietnamese with 61,446 references show that our proposed model performs better results than several strong baselines and achieves an F 1 score of 99.4% for the joint reference and relation extraction task.Keywords
This publication has 22 references indexed in Scilit:
- CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task LearningProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Reference Extraction from Vietnamese Legal Documents2019
- Joint Learning of Named Entity Recognition and Entity Linking2019
- Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism2018
- Joint entity and relation extraction based on a hybrid neural networkNeurocomputing, 2017
- Automated reference resolution in legal textsArtificial Intelligence and Law, 2013
- Reference Extraction and Resolution for Legal TextsLecture Notes in Computer Science, 2005
- Automated extraction of normative references in legal texts2003
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955