Incremental Personalised Summarisation with Novelty Detection

  • Authors:
  • Marco Campana;Anastasios Tombros

  • Affiliations:
  • Queen Mary University of London, London, United Kingdom E1 4NS;Queen Mary University of London, London, United Kingdom E1 4NS

  • Venue:
  • FQAS '09 Proceedings of the 8th International Conference on Flexible Query Answering Systems
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In recent years personalised summarisation has been a hot research topic. Personalised summarisation techniques often attach high importance to query terms in order to customise summaries to user interests (e.g. query-biased summarisation). However, the query string is not always enough to represent the user's interests, and a more complex representation is needed. We present in this paper a novel summarisation method that makes use of a more complex user modelling process to provide summaries that dynamically adapt to the user's interests. The user model is created and updated by analysing the interaction of the user with a search system, and then used to create personalised summaries. The system also allows the user to extend initial summaries to broader summaries that contain novel information. We demonstrate our technique using a blogging system. Results of a system-centric and user-centric evaluation suggest that the proposed summarisation method performs better than query-biased summarisation in extracting relevant sentences from a document, thus showing that adaptive summarisation is an effective way to support the user in the relevance judgment process.