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.
|Title of host publication||The Tenth International Conference on Artificial Intelligence and Law, Proceedings of the Conference, June 6-11, 2005, Bologna, Italy|
|Number of pages||10|
|Publication status||Published - 2005|