Automatic legal text summarisation: experiments with summary structuring

ABSTRACT

We describe a set of experiments using machine learning techniques for the task of extractive summarisation. The research is part of a summarisation project for which we use a corpus of judgments of the UK House of Lords. We present classification results for naïve Bayes and maximum entropy and we explore methods for scoring the summary-worthiness of a sentence. We present sample output from the system, illustrating the utility of rhetorical status information, which provides a means for structuring summaries and tailoring them to different types of users.

REFERENCES

• 1: C. Aone, M. E. Okurowski, J. Gorlinsky, and B. Larsen. A trainable summarizer with knowledge acquired from robust NLP techniques. In I. Mani and M. T. Maybury, editors, Advances in Automatic Text Summarization, pages 71--80. MIT Press, Cambridge, Massechusetts, 1999.
• 2: M. Banko, V. Mittal, M. Kantrowitz, and J. Goldstein. Generating extraction-based summaries from hand-written summaries by aligning text spans. In Proceedings of the Pacific Association for Computational Linguistics, 1999.
• 3: J. Carletta, S. Evert, U. Heid, J. Kilgour, J. Robertson, and H. Voormann. The nite xml toolkit: flexible annotation for multi-modal language data. Behavior Research Methods, Instruments, and Computers, special issue on Measuring Behavior, 35(3), 2003.
• 4: U. Fayyad and K. Irani. Multi-interval discretization of continuous-valued attributes for classification learning. In Proceedings of the 13th International Joint Conference on Artificial Intelligence, 1993.
• 5: C. Grover, B. Hachey, and I. Hughson. The HOLJ corpus: supporting summarisation of legal texts. In Proceedings of the 5th International Workshop on Linguistically Interpreted Corpora, Geneva, Switzerland, 2004.
• 6: Claire Grover , Ben Hachey , Ian Hughson , Chris Korycinski, Automatic summarisation of legal documents, Proceedings of the 9th international conference on Artificial intelligence and law, June 24-28, 2003, Scotland, United Kingdom [doi>10.1145/1047788.1047839]
• 7: B. Hachey and C. Grover. A rhetorical status classifier for legal text summarisation. In Proceedings of the ACL-2004 Text Summarization Branches Out Workshop, 2004.
• 8: Ben Hachey , Claire Grover, Sequence modelling for sentence classification in a legal summarisation system, Proceedings of the 2005 ACM symposium on Applied computing, March 13-17, 2005, Santa Fe, New Mexico [doi>10.1145/1066677.1066746]
• 9: Hongyan Jing , Kathleen R. McKeown, The decomposition of human-written summary sentences, Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, p.129-136, August 15-19, 1999, Berkeley, California, United States [doi>10.1145/312624.312666]
• 10: G. H. John and P. Langley. Esitmating continuous distributions in bayesian classifiers. In Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence, 1995.
• 11: Julian Kupiec , Jan Pedersen , Francine Chen, A trainable document summarizer, Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval, p.68-73, July 09-13, 1995, Seattle, Washington, United States [doi>10.1145/215206.215333]
• 12: Robert Malouf, A comparison of algorithms for maximum entropy parameter estimation, proceeding of the 6th conference on Natural language learning, p.1-7, August 31, 2002 [doi>10.3115/1118853.1118871]
• 13: Inderjeet Mani , Eric Bloedorn, Machine learning of generic and user-focused summarization, Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence, p.820-826, July 1998, Madison, Wisconsin, United States
• 14: Daniel Marcu, The automatic construction of large-scale corpora for summarization research, Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, p.137-144, August 15-19, 1999, Berkeley, California, United States [doi>10.1145/312624.312668]
• 15: S. Teufel and M. Moens. Sentence extraction as a classification task. In ACL-1997 Workshop on Intelligent and Scalable Text Summarization, 1997.
• 16: Simone Teufel , Jean Carletta , Marc Moens, An annotation scheme for discourse-level argumentation in research articles, Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics, June 08-12, 1999, Bergen, Norway [doi>10.3115/977035.977051]
• 17: Simone Teufel , Marc Moens, Summarizing scientific articles: experiments with relevance and rhetorical status, Computational Linguistics, v.28 n.4, p.409-445, December 2002 [doi>10.1162/089120102762671936]
• 18: Mark Wasson, Using leading text for news summaries: evaluation results and implications for commercial summarization applications, Proceedings of the 36th annual meeting on Association for Computational Linguistics, p.1364-1368, August 10-14, 1998, Montreal, Quebec, Canada

INDEX TERMS

Keywords:
automatic summarisation, discourse, machine learning, natural language