A Graph-based Approach to Cross-language Multi-document Summarization

Abstract : Cross-language summarization is the task of generating a summary in a language different from the language of the source documents. In this paper, we propose a graph-based approach to multi-document summarization that integrates machine translation quality scores in the sentence extraction process. We evaluate our method on a manually translated subset of the DUC 2004 evaluation campaign. Results indicate that our approach improves the readability of the generated summaries without degrading their informativity. Index Terms-Graph-based approach, cross-language multi-document summarization.
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02021891
Contributor : Stéphane Huet <>
Submitted on : Tuesday, February 26, 2019 - 12:07:30 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM
Long-term archiving on : Monday, May 27, 2019 - 12:39:38 PM

File

Polibits11.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-02021891, version 1

Collections

Citation

Florian Boudin, Stéphane Huet, Juan-Manuel Torres-Moreno. A Graph-based Approach to Cross-language Multi-document Summarization. 12th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing), 2011, Tokyo, Japan. pp.113-118. ⟨hal-02021891⟩

Share

Metrics

Record views

37

Files downloads

21