CNN for Text-Based Multiple Choice Question Answering - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

CNN for Text-Based Multiple Choice Question Answering

Résumé

The task of Question Answering is at the very core of machine comprehension. In this paper, we propose a Convolutional Neural Network (CNN) model for text-based multiple choice question answering where questions are based on a particular article. Given an article and a multiple choice question, our model assigns a score to each question-option tuple and chooses the final option accordingly. We test our model on Textbook Question Answering (TQA) and SciQ dataset. Our model outperforms several LSTM-based baseline models on the two datasets.
Fichier principal
Vignette du fichier
acl18.pdf (293.53 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02265065 , version 1 (08-08-2019)

Identifiants

  • HAL Id : hal-02265065 , version 1

Citer

Akshay Chaturvedi, Onkar Pandit, Utpal Garain. CNN for Text-Based Multiple Choice Question Answering. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Jul 2018, Melbourne, Australia. pp.272 - 277. ⟨hal-02265065⟩
166 Consultations
648 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More