Asymmetry Sensitive Architecture for Neural Text Matching - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Asymmetry Sensitive Architecture for Neural Text Matching

Résumé

Question-answer matching can be viewed as a puzzle where missing pieces of information are provided by the answer. To solve this puzzle, one must understand the question to find out a correct answer. Semantic-based matching models rely mainly in semantic relatedness the input text words. We show that beyond the semantic similarities, matching models must focus on the most important words to find the correct answer. We use attention-based models to take into account the word saliency and propose an asymmetric architecture that focuses on the most important words of the question or the possible answers. We extended several state-of-the-art models with an attention-based layer. Experimental results, carried out on two QA datasets, show that our asymmetric architecture improves the performances of well-known neural matching algorithms.
Fichier principal
Vignette du fichier
belkacem_24976.pdf (406.06 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02435348 , version 1 (10-01-2020)

Identifiants

  • HAL Id : hal-02435348 , version 1
  • OATAO : 24976

Citer

Thiziri Belkacem, Jose G. Moreno, Taoufiq Dkaki, Mohand Boughanem. Asymmetry Sensitive Architecture for Neural Text Matching. 41st European Conference on Information Retrieval (ECIR 2019), Apr 2019, Cologne, Germany. pp.62-69. ⟨hal-02435348⟩
35 Consultations
78 Téléchargements

Partager

Gmail Facebook X LinkedIn More