Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression

Résumé

Multi-Sentence Compression (MSC) is the task of generating a short single sentence summary from a cluster of related sentences. This paper presents an N-best reranking method based on keyphrase extraction. Compression candidates generated by a word graph-based MSC approach are reranked according to the number and relevance of keyphrases they contain. Both manual and automatic evaluations were performed using a dataset made of clusters of newswire sentences. Results show that the proposed method significantly improves the informativity of the generated compressions.
Fichier principal
Vignette du fichier
msc.pdf (144.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00816353 , version 1 (22-04-2013)

Identifiants

  • HAL Id : hal-00816353 , version 1

Citer

Florian Boudin, Emmanuel Morin. Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression. North American Chapter of the Association for Computational Linguistics (NAACL), Jun 2013, Atlanta, United States. ⟨hal-00816353⟩
547 Consultations
623 Téléchargements

Partager

Gmail Facebook X LinkedIn More