Abstract | ||
---|---|---|
Identifying contradictory statements in legal proceedings is largely manual in nature. Automating this using intelligent techniques such as natural language model will not only save a lot of time but also aid in the process of solving legal cases. This paper aims at creating an artificial intelligent (AI) model that can identify contradictory sentences in legal proceedings. The novelty of this study is the construction of a new dataset that represents neutral and contradictory statements that may be given in the legal proceedings. We give a comparative study of the various pre-trained Natural Language Models such as ELMo, Google BERT, XLNet, and Google ALBERT to understand and identify contradictory statements made by people in legal proceedings. We achieve the highest accuracy of 88.0% in identifying contradictory statements using the Google ALBERT model. This model can be implemented on a real-time basis and hence has practical applicability. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/s42979-022-01075-3 | SN Computer Science |
Keywords | DocType | Volume |
Classification, Contradiction, Natural language understanding, Legal proceedings | Journal | 3 |
Issue | ISSN | Citations |
3 | 2662-995X | 1 |
PageRank | References | Authors |
0.37 | 1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Surana Shraddha | 1 | 1 | 0.37 |
Dembla Sugam | 2 | 1 | 0.37 |
Bihani Prateek | 3 | 1 | 0.37 |