Predicting and Integrating Expected Answer Types into a Simple Recurrent Neural Network Model for Answer Sentence Selection - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Predicting and Integrating Expected Answer Types into a Simple Recurrent Neural Network Model for Answer Sentence Selection

Résumé

Since end-to-end deep learning models have started to replace traditional pipeline architectures of question answering systems, features such as expected answer types which are based on the question semantics are seldom used explicitly in the models. In this paper, we propose a convolution neural network model to predict these answer types based on question words and a recurrent neural network model to find sentence similarity scores between question and answer sentences. The proposed model outperforms the current state of the art results on an answer sentence selection task in open domain question answering by 1.88% on MAP and 2.96% on MRR scores.
Fichier principal
Vignette du fichier
CICLING_2019_PAPER(3).pdf (273.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02104488 , version 1 (19-04-2019)

Identifiants

  • HAL Id : hal-02104488 , version 1

Citer

Sanjay Kamath, Brigitte Grau, Yue Ma. Predicting and Integrating Expected Answer Types into a Simple Recurrent Neural Network Model for Answer Sentence Selection. 20th International Conference on Computational Linguistics and Intelligent Text Processing, Apr 2019, La Rochelle, France. ⟨hal-02104488⟩
666 Consultations
1090 Téléchargements

Partager

Gmail Facebook X LinkedIn More