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

Abstract : 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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02104488
Contributor : Sanjay Kamath Ramachandra Rao <>
Submitted on : Friday, April 19, 2019 - 3:19:51 PM
Last modification on : Friday, May 3, 2019 - 4:56:48 PM

File

CICLING_2019_PAPER(3).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02104488, version 1

Citation

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⟩

Share

Metrics

Record views

94

Files downloads

57