Rule Induction for Sentence Reduction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Rule Induction for Sentence Reduction

Résumé

Sentence Reduction has recently received a great attention from the research community of Automatic Text Summarization. Sentence Reduction con- sists in the elimination of sentence components such as words, part-of-speech tags sequences or chunks without highly deteriorating the information contained in the sentence and its grammatical correctness. In this paper, we present an unsu- pervised scalable methodology for learning sentence reduction rules. Paraphrases are first discovered within a collection of automatically crawled Web News Sto- ries and then textually aligned in order to extract interchangeable text fragment candidates, in particular reduction cases . As only positive examples exist, In- ductive Logic Programming (ILP) provides an interesting learning paradigm for the extraction of sentence reduction rules . As a consequence, reduction cases are transformed into first order logic clauses to supply a massive set of suitable learn- ing instances and an ILP learning environment is defined within the context of the Aleph framework. Experiments evidence good results in terms of irrelevancy elimination, syntactical correctness and reduction rate in a real-world environ- ment as opposed to other methodologies proposed so far.
Fichier principal
Vignette du fichier
ACTI-DIAS-2013-1.pdf (212.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01073200 , version 1 (09-10-2014)

Identifiants

Citer

João-Paolo Cordeiro, Gaël Dias, Pavel Brazdil. Rule Induction for Sentence Reduction. 16th Portuguese Conference in Artificial Intelligence (EPIA 2013), Sep 2013, Azores, Portugal. pp 528-539, ⟨10.1007/978-3-642-40669-0_45⟩. ⟨hal-01073200⟩
128 Consultations
125 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More