Automated Attribute Extraction from Legal Proceedings
Authors:
- Subinay AdhikarySASubinay Adhikary
- Sagnik DasSDSagnik Das
- Sagnik SahaSSSagnik Saha
- Procheta SenPSProcheta Sen
- Dwaipayan RoyDRDwaipayan Roy
- Kripabandhu GhoshKGKripabandhu Ghosh
Preprint
Abstract
The escalating number of pending cases is a growing concern world-wide. Recent advancements in digitization have opened up possibilities for leveraging artificial intelligence (AI) tools in the processing of legal documents. Adopting a structured representation for legal documents, as opposed to a mere bag-of-words flat text representation, can significantly enhance processing capabilities. With the aim of achieving this objective, we put forward a set of diverse attributes for criminal case proceedings. We use a state-of-the-art sequence labeling framework to automatically extract attributes from the legal documents. Moreover, we demonstrate the efficacy of the extracted attributes in a downstream task, namely legal judgment prediction.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Effective deep learning approaches for summarization of legal textsJournal of King Saud University Computer and Information Sciences, 2022
- Named Entity Recognition in Indian court judgments2022
- Improving biomedical named entity recognition with syntactic informationBMC Bioinformatics, 2020
- Identification of Rhetorical Roles of Sentences in Indian Legal Judgments2019
- An Overview of Named Entity Recognition2018
- The use of ontologies for effective knowledge modelling and information retrievalApplied Computing and Informatics, 2018
- Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens2018
- What Are Ontologies Good For?2013