Question Answering and Question Generation as Dual Tasks

TL;DR

This paper introduces a dual-task training framework for joint question answering and question generation, leveraging their intrinsic connection to mutually improve both tasks through probabilistic correlation.

Contribution

The paper proposes a novel dual-task training approach that explicitly models the probabilistic relationship between QA and QG, enhancing both models' performance.

Findings

Improved performance of QA and QG models on three datasets.

Joint training outperforms separate models and baseline approaches.

Framework is fully differentiable and trainable via backpropagation.

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.