Question Answering and Question Generation as Dual Tasks

Abstract

We study the problem of joint question answering (QA) and question generation (QG) in this paper. Our intuition is that QA and QG have intrinsic connections and these two tasks could improve each other. On one side, the QA model judges whether the generated question of a QG model is relevant to the answer. On the other side, the QG model provides the probability of generating a question given the answer, which is a useful evidence that in turn facilitates QA. In this paper we regard QA and QG as dual tasks. We propose a training framework that trains the models of QA and QG simultaneously, and explicitly leverages their probabilistic correlation to guide the training process of both models. We implement a QG model based on sequence-to-sequence learning, and a QA model based on recurrent neural network. As all the components of the QA and QG models are differentiable, all the parameters involved in these two models could be conventionally learned with back propagation. We conduct experiments on three datasets. Empirical results show that our training framework improves both QA and QG tasks. The improved QA model performs comparably with strong baseline approaches on all three datasets.

References in corpus (5)

• ADADELTA: An Adaptive Learning Rate Method
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Deep Learning for Answer Sentence Selection
• Encoding Source Language with Convolutional Neural Network for Machine Translation
• Question Generation from a Knowledge Base with Web Exploration

Cited by in corpus (5)

• Visual Question Generation as Dual Task of Visual Question Answering
• DAL: Dual Adversarial Learning for Dialogue Generation
• Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
• Semantic Parsing with Dual Learning
• Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism