Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021 |
| Seiten | 22-31 |
| Seitenumfang | 10 |
| ISBN (elektronisch) | 9781450385268 |
| Publikationsstatus | Veröffentlicht - 27 Juli 2021 |
| Veranstaltung | 18th International Conference on Artificial Intelligence and Law, ICAIL 2021 - Virtual, Online, Brasilien Dauer: 21 Juni 2021 → 25 Juni 2021 |
Publikationsreihe
| Name | Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021 |
|---|
Abstract
Automatic summarization of legal case documents is an important and practical challenge. Apart from many domain-independent text summarization algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal case documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, we propose an unsupervised summarization algorithm DELSumm which is designed to systematically incorporate guidelines from legal experts into an optimization setup. We conduct detailed experiments over case documents from the Indian Supreme Court. The experiments show that our proposed unsupervised method outperforms several strong baselines in terms of ROUGE scores, including both general summarization algorithms and legal-specific ones. In fact, though our proposed algorithm is unsupervised, it outperforms several supervised summarization models that are trained over thousands of document-summary pairs.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Software
- Sozialwissenschaften (insg.)
- Recht
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021. 2021. S. 22-31 (Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Incorporating domain knowledge for extractive summarization of legal case documents
AU - Bhattacharya, Paheli
AU - Poddar, Soham
AU - Rudra, Koustav
AU - Ghosh, Kripabandhu
AU - Ghosh, Saptarshi
N1 - Funding Information: Acknowledgements: The authors thank the Law experts from the Rajiv Gandhi School of Intellectual Property Law, India who helped in developing the gold standard data and provided the guidelines for summarization. The research is partially supported by the TCG Centres for Research and Education in Science and Technology (CREST) through the project titled ‘Smart Legal Consultant: AI-based Legal Analytics’. Thiswork isalsosupported inpartby theEuropean Union’s Horizon 2020 research and innovation programme under grant agreement No 832921. P. Bhattacharya is supported by a Fellowship from Tata Consultancy Services.
PY - 2021/7/27
Y1 - 2021/7/27
N2 - Automatic summarization of legal case documents is an important and practical challenge. Apart from many domain-independent text summarization algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal case documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, we propose an unsupervised summarization algorithm DELSumm which is designed to systematically incorporate guidelines from legal experts into an optimization setup. We conduct detailed experiments over case documents from the Indian Supreme Court. The experiments show that our proposed unsupervised method outperforms several strong baselines in terms of ROUGE scores, including both general summarization algorithms and legal-specific ones. In fact, though our proposed algorithm is unsupervised, it outperforms several supervised summarization models that are trained over thousands of document-summary pairs.
AB - Automatic summarization of legal case documents is an important and practical challenge. Apart from many domain-independent text summarization algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal case documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, we propose an unsupervised summarization algorithm DELSumm which is designed to systematically incorporate guidelines from legal experts into an optimization setup. We conduct detailed experiments over case documents from the Indian Supreme Court. The experiments show that our proposed unsupervised method outperforms several strong baselines in terms of ROUGE scores, including both general summarization algorithms and legal-specific ones. In fact, though our proposed algorithm is unsupervised, it outperforms several supervised summarization models that are trained over thousands of document-summary pairs.
KW - integer linear programming
KW - legal document summarization
UR - http://www.scopus.com/inward/record.url?scp=85112387162&partnerID=8YFLogxK
U2 - 10.1145/3462757.3466092
DO - 10.1145/3462757.3466092
M3 - Conference contribution
AN - SCOPUS:85112387162
T3 - Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021
SP - 22
EP - 31
BT - Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021
T2 - 18th International Conference on Artificial Intelligence and Law, ICAIL 2021
Y2 - 21 June 2021 through 25 June 2021
ER -