An Approach Towards Question Answering Using Apposite Context

3 Pages Posted: 3 Sep 2019

See all articles by Lakshmi K

Lakshmi K

Government Engineering College, Sreekrishnapuram - Department of Computer Science and Engineering

Raseek

Government Engineering College, Sreekrishnapuram

Date Written: August 31, 2019

Abstract

Question Answering (QA) is concerned with building systems that automatically answer questions given by humans in a natural language. Most of the successful approaches for these systems rely on Recurrent Neural Networks (RNNs). But, running them over long documents is prohibitively slow. Traditional models for QA optimize using cross entropy loss on the start and end positions of the answer. But, these models do not consider word overlapping between actual and predicted ones and thus, may results in wrong output. The proposed system puts forward a QA model that combines cross entropy loss with word overlapping. Another significance is that, the context being fed into the QA model is shortened by selecting only the relevant sentences with respect to the input question, from the source document. The model is implemented with the aid of a mechanism called Dynamic Coattention Network (DCN). Dataset used for the implementation of this system is Stanford Question Answering Dataset (SQuAD).

Keywords: Question Answering, Deep Neural Networks, Sentence selectors, Answer Generators, Natural Language Processing

Suggested Citation

K, Lakshmi and C, Raseek, An Approach Towards Question Answering Using Apposite Context (August 31, 2019). In proceedings of the International Conference on Systems, Energy & Environment (ICSEE) 2019, GCE Kannur, Kerala, July 2019. Available at SSRN: https://ssrn.com/abstract=3445866 or http://dx.doi.org/10.2139/ssrn.3445866

Lakshmi K (Contact Author)

Government Engineering College, Sreekrishnapuram - Department of Computer Science and Engineering

India

Raseek C

Government Engineering College, Sreekrishnapuram ( email )

India

Register to save articles to
your library

Register

Paper statistics

Downloads
6
Abstract Views
83
PlumX Metrics