Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions

Yang Zhong, Diane Litman


Abstract
Though many algorithms can be used to automatically summarize legal case decisions, most fail to incorporate domain knowledge about how important sentences in a legal decision relate to a representation of its document structure. For example, analysis of a legal case sum- marization dataset demonstrates that sentences serving different types of argumentative roles in the decision appear in different sections of the document. In this work, we propose an unsupervised graph-based ranking model that uses a reweighting algorithm to exploit properties of the document structure of legal case decisions. We also explore the impact of using different methods to compute the document structure. Results on the Canadian Legal Case Law dataset show that our proposed method outperforms several strong baselines.
Anthology ID:
2022.nllp-1.30
Volume:
Proceedings of the Natural Legal Language Processing Workshop 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Nikolaos Aletras, Ilias Chalkidis, Leslie Barrett, Cătălina Goanță, Daniel Preoțiuc-Pietro
Venue:
NLLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
322–337
Language:
URL:
https://aclanthology.org/2022.nllp-1.30
DOI:
10.18653/v1/2022.nllp-1.30
Bibkey:
Cite (ACL):
Yang Zhong and Diane Litman. 2022. Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions. In Proceedings of the Natural Legal Language Processing Workshop 2022, pages 322–337, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions (Zhong & Litman, NLLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.nllp-1.30.pdf
Video:
 https://aclanthology.org/2022.nllp-1.30.mp4