Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/131662
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Label definitions augmented interaction model for legal charge prediction |
Author: | Kang, L. Liu, J. Liu, L. Ye, D. |
Citation: | Lecture Notes in Artificial Intelligence, 2021, vol.12656, pp.270-283 |
Publisher: | Springer |
Publisher Place: | Cham, Switzerland |
Issue Date: | 2021 |
Series/Report no.: | Lecture Notes in Computer Science; 12656 |
ISBN: | 9783030721121 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | European Conference on Information Retrieval (ECIR) (28 Mar 2021 - 1 Apr 2021 : virtual online) |
Statement of Responsibility: | Liangyi Kang, Jie Liu, Lingqiao Liu, Dan Ye |
Abstract: | Charge prediction, determining charges for cases by analyzing the textual fact descriptions, is a fundamental technology in legal information retrieval systems. In practice, the fact descriptions could exhibit a significant intra-class variation due to factors like non-normative use of language by different users, which makes the prediction task very challenging, especially for charge classes with too few samples to cover the expression variation. In this work, we explore to use the charge (label) definitions to alleviate this issue. The key idea is that the expressions in a fact description should have corresponding formal terms in label definitions, and those terms are shared across classes and could account for the diversity in the fact descriptions. Thus, we propose to create auxiliary fact representations from charge definitions to augment fact descriptions representation. Specifically, we design label definitions augmented interaction model, where fact description interacts with the relevant charge definitions and terms in those definitions by a sentence- and word-level attention scheme, to generated auxiliary representations. Experimental results on two datasets show that our model achieves significant improvement than baselines, especially for dataset with few samples. |
Keywords: | Legal charge prediction; Label definitions; Interaction model; Auxiliary representation; Augmented fact representation |
Rights: | © Springer Nature Switzerland AG 2021 |
DOI: | 10.1007/978-3-030-72113-8_18 |
Published version: | https://link.springer.com/book/10.1007/978-3-030-72113-8 |
Appears in Collections: | Aurora harvest 4 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.