Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering

TL;DR

This paper investigates neural network models for question understanding and adaptation in question answering, introducing syntactic encoding and question-type modeling to improve performance on SQuAD.

Contribution

It presents novel neural network approaches that incorporate syntactic information and question-type adaptation for enhanced question answering.

Findings

Improved accuracy on SQuAD dataset.

Effective modeling of question types and shared information.

Syntactic encoding enhances question comprehension.

Abstract

The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA). In this paper, we approach the problems by closely modelling questions in a neural network framework. We first introduce syntactic information to help encode questions. We then view and model different types of questions and the information shared among them as an adaptation task and proposed adaptation models for them. On the Stanford Question Answering Dataset (SQuAD), we show that these approaches can help attain better results over a competitive baseline.