Interactive Learning for Text Summarization

Massih-Reza Amini
Laboratoire d'Informatique Paris 6
case 169
4, place de Jussieu
75252 Paris cedex 05

The paper describes a query-relevant text summary based on interactive learning. The system proceeds in two steps, it first extracts the most relevant sentences of a document with regard to a user query using a classical tf-idf term weighting scheme, it then learns the user feedback in order to improve its performances. Learning operates at two levels: query expansion and sentence scoring.