Sentence extraction for legal text summarisation

Ben Hachey; Claire Grover

Sentence extraction for legal text summarisation

Ben Hachey, Claire Grover

School of Computing

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

We describe a system for generating extractive summaries of texts in the legal domain, focusing on the relevance classifier, which determines which sentences are abstract-worthy. We experiment with naïve Bayes and maximum entropy estimation toolkits and explore methods for selecting abstract-worthy sentences in rank order. Evaluation using standard accuracy measures and using correlation confirm the utility of our approach, but suggest different optimal configurations.

Original language	English
Pages (from-to)	1686-1687
Number of pages	2
Journal	IJCAI International Joint Conference on Artificial Intelligence
Publication status	Published - 2005

Cite this

@article{5ad5aadcce4f424797a2a938b7409326,

title = "Sentence extraction for legal text summarisation",

abstract = "We describe a system for generating extractive summaries of texts in the legal domain, focusing on the relevance classifier, which determines which sentences are abstract-worthy. We experiment with na{\"i}ve Bayes and maximum entropy estimation toolkits and explore methods for selecting abstract-worthy sentences in rank order. Evaluation using standard accuracy measures and using correlation confirm the utility of our approach, but suggest different optimal configurations.",

author = "Ben Hachey and Claire Grover",

year = "2005",

language = "English",

pages = "1686--1687",

journal = "IJCAI International Joint Conference on Artificial Intelligence",

issn = "1045-0823",

publisher = "Association for the Advancement of Artificial Intelligence",

}

TY - JOUR

T1 - Sentence extraction for legal text summarisation

AU - Hachey, Ben

AU - Grover, Claire

PY - 2005

Y1 - 2005

N2 - We describe a system for generating extractive summaries of texts in the legal domain, focusing on the relevance classifier, which determines which sentences are abstract-worthy. We experiment with naïve Bayes and maximum entropy estimation toolkits and explore methods for selecting abstract-worthy sentences in rank order. Evaluation using standard accuracy measures and using correlation confirm the utility of our approach, but suggest different optimal configurations.

AB - We describe a system for generating extractive summaries of texts in the legal domain, focusing on the relevance classifier, which determines which sentences are abstract-worthy. We experiment with naïve Bayes and maximum entropy estimation toolkits and explore methods for selecting abstract-worthy sentences in rank order. Evaluation using standard accuracy measures and using correlation confirm the utility of our approach, but suggest different optimal configurations.

UR - http://www.scopus.com/inward/record.url?scp=84880716553&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84880716553

SN - 1045-0823

SP - 1686

EP - 1687

JO - IJCAI International Joint Conference on Artificial Intelligence

JF - IJCAI International Joint Conference on Artificial Intelligence

ER -

Sentence extraction for legal text summarisation

Abstract

Other files and links

Fingerprint

Cite this