Skip to Main content Skip to Navigation
Conference papers

Transductive Learning over Automatically Detected Themes for Multi-Document Summarization

Massih-Reza Amini 1 Nicolas Usunier 1
1 MALIRE - Machine Learning and Information Retrieval
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : We propose a new method for query-biased multi-document summarization, based on sentence extraction. The summary of multiple documents is created in two steps. Sentences are first clustered; where each cluster corresponds to one of the main themes present in the collection. Inside each theme, sentences are then ranked using a transductive learning-to-rank algorithm based on RankNet, in order to better identify those which are relevant to the query. The final summary contains the top-ranked sentences of each theme. Our approach is validated on DUC 2006 and DUC 2007 datasets.
Document type :
Conference papers
Complete list of metadata
Contributor : Lip6 Publications <>
Submitted on : Thursday, March 10, 2016 - 1:36:53 PM
Last modification on : Friday, January 8, 2021 - 5:34:11 PM



Massih-Reza Amini, Nicolas Usunier. Transductive Learning over Automatically Detected Themes for Multi-Document Summarization. The 34th Annual ACM SIGIR Conference (SIGIR 2011), Jul 2011, Beijing, China. pp.1193-1194, ⟨10.1145/2009916.2010115⟩. ⟨hal-01286161⟩



Record views