L2QA: Long Legal Article Question Answering with Cascaded Key Segment Learning
Paper
Xie, Shugui, Li, Lin, Yuan, Jingling, Xie, Qing and Tao, Xiaohui. 2023. "L2QA: Long Legal Article Question Answering with Cascaded Key Segment Learning." 28th International Conference on Database Systems for Advanced Applications (DASFAA 2023). Tianjin, China 17 - 20 Apr 2023 Springer. https://doi.org/10.1007/978-3-031-30675-4_27
Paper/Presentation Title | L2QA: Long Legal Article Question Answering with Cascaded Key Segment Learning |
---|---|
Presentation Type | Paper |
Authors | Xie, Shugui, Li, Lin, Yuan, Jingling, Xie, Qing and Tao, Xiaohui |
Journal or Proceedings Title | Proceedings of 28th International Conference on Database Systems for Advanced Applications (DASFAA 2023) |
Journal Citation | 13945, pp. 385-394 |
Number of Pages | 10 |
Year | 2023 |
Publisher | Springer |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-031-30675-4_27 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-031-30675-4_27 |
Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-3-031-30675-4 |
Conference/Event | 28th International Conference on Database Systems for Advanced Applications (DASFAA 2023) |
Event Details | 28th International Conference on Database Systems for Advanced Applications (DASFAA 2023) Parent Database Systems for Advanced Applications Delivery In person Event Date 17 to end of 20 Apr 2023 Event Location Tianjin, China |
Abstract | Evidences in Legal Question Answering (LQA) help infer accurate answers. Current sentence-level evidence extraction based methods may lose the discourse coherence of legal articles since they tend to make the extracted sentences scattered over an article. To this end, this paper proposes a cascaded key segment learning enhanced framework for L ong L egal article Q uestion A nswering, namely L2QA. The framework consists of three cascaded modules: Sifter, Reader, and Responder, which first transfers a long legal article into segments and each segment is inherent in the discourse coherence from consecutive sentences. And then, the Sifter is trained by automatically sifting out key segments in an iterative answer-guided coarse-to-fine way. The Reader utilizes a range of co-attention and self-attention mechanisms to obtain the semantic representations of the question and key segments. Finally, the Responder predicts final answers in a cascaded manner, identifying where the answer is located. Conducted on CAIL 2021 Law MRC dataset, our L2QA achieves 83.1 Macro-F1 and 65.8 EM and outperforms a state-of-the-art legal QA model by 4.1% and 9.1%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. |
Keywords | Coarse-to-fine; Legal Question Answering; Key Segment |
ANZSRC Field of Research 2020 | 460508. Information retrieval and web search |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Series | Lecture Notes in Computer Science |
Byline Affiliations | Wuhan University of Technology, China |
University of Southern Queensland |
Permalink -
https://research.usq.edu.au/item/z2770/l2qa-long-legal-article-question-answering-with-cascaded-key-segment-learning
51
total views0
total downloads0
views this month0
downloads this month