Automatic Legal Text Summarisation: Experiments with Summary Structuring

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 na¨ıve 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. Keywords Automatic summarisation, Discourse, Natural language, Machine learning

• Type: Conference
• Year: 2005
• Where: ICAIL
• Authors: Ben Hachey, Claire Grover
• Keywords: Extractive Summarisation, ICAIL 2005, Machine Learning, Summarisation Project