A Multilingual Study of Compressive Cross-Language Text Summarization

Abstract : Cross-Language Text Summarization generates summaries in a language different from the language of the source documents. Recent methods use information from both languages to generate summaries with the most informative sentences. However, these methods have performance that can vary according to languages, which can reduce the quality of summaries. In this paper, we propose a compressive framework to generate cross-language summaries. In order to analyze performance and especially stability, we tested our system and extrac-tive baselines on a dataset available in four languages (English, French, Portuguese, and Spanish) to generate English and French summaries. An automatic evaluation showed that our method outperformed extractive state-of-art CLTS methods with better and more stable ROUGE scores for all languages.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02021602
Contributor : Stéphane Huet <>
Submitted on : Saturday, February 16, 2019 - 1:02:41 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM
Long-term archiving on : Friday, May 17, 2019 - 2:25:34 PM

File

MICAI18.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Elvys Linhares Pontes, Stéphane Huet, Juan-Manuel Torres-Moreno. A Multilingual Study of Compressive Cross-Language Text Summarization. 17th Mexican International Conference on Artificial Intelligence (MICAI), 2018, Guadalajara, Mexico. pp.109-118, ⟨10.1007/978-3-030-04497-8_9⟩. ⟨hal-02021602⟩

Share

Metrics

Record views

19

Files downloads

8