Singh, Vivek Kumar (2022) Explainable Statute Prediction. Masters thesis, Indian Institute of Science Education and Research Kolkata.
Text (MS dissertation of Vivek Kumar Singh (16MS204))
16MS204_Thesis_file.pdf - Submitted Version Restricted to Repository staff only Download (1MB) |
Abstract
This work deals with an analysis of using artificial intelligence and machine learning for statute prediction in the Indian legal domain. Furthermore, we try to identify the issues that limit the prediction performance and address them. Alongside the prediction task, we generate explanations for the predictions and compare the performance with a human expert. We reproduce as well as develop some methodologies for explainability. We further prepare an annotated dataset over the Indian legal domain that can be used for problems related to statute prediction and explainability. We discuss in detail the development of this dataset and its potential use-cases. Furthermore we discuss approaches to combine statute prediction task with explainability task and tackle it using different methods.
Item Type: | Thesis (Masters) |
---|---|
Additional Information: | Supervisor: Dr. Kripabandhu Ghosh; Co-Supervisor: Dr. Satyaki Mazumder |
Uncontrolled Keywords: | Artificial Intelligence; Indian Legal Domain; Machine Learning; Statute Prediction |
Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | Department of Mathematics and Statistics |
Depositing User: | IISER Kolkata Librarian |
Date Deposited: | 05 Sep 2022 07:38 |
Last Modified: | 05 Sep 2022 07:38 |
URI: | http://eprints.iiserkol.ac.in/id/eprint/1171 |
Actions (login required)
View Item |