Skip to Main content Skip to Navigation
Conference papers

Asymmetry Sensitive Architecture for Neural Text Matching

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, January 10, 2020 - 5:14:43 PM
Last modification on : Saturday, June 13, 2020 - 8:02:54 AM


Files produced by the author(s)


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


Thiziri Belkacem, José 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⟩



Record views


Files downloads