Learning to Generate Questions by Learning What not to Generate

Abstract

Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing neural question generation models are not sufficient mainly due to their inability to properly model the process of how each word in the question is selected, i.e., whether repeating the given passage or being generated from a vocabulary. In this paper, we propose our Clue Guided Copy Network for Question Generation (CGC-QG), which is a sequence-to-sequence generative model with copying mechanism, yet employing a variety of novel components and techniques to boost the performance of question generation. In CGC-QG, we design a multi-task labeling strategy to identify whether a question word should be copied from the input passage or be generated instead, guiding the model to learn the accurate boundaries between copying and generation. Furthermore, our input passage encoder takes as input, among a diverse range of other features, the prediction made by a clue word predictor, which helps identify whether each word in the input passage is a potential clue to be copied into the target question. The clue word predictor is designed based on a novel application of Graph Convolutional Networks onto a syntactic dependency tree representation of each passage, thus being able to predict clue words only based on their context in the passage and their relative positions to the answer in the tree. We jointly train the clue prediction as well as question generation with multi-task learning and a number of practical strategies to reduce the complexity. Extensive evaluations show that our model significantly improves the performance of question generation and out-performs all previous state-of-the-art neural question generation models by a substantial margin.

arXiv commentAccepted by WWW 2019

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Semi-Supervised Classification with Graph Convolutional Networks
• Categorical Reparameterization with Gumbel-Softmax
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Question Answering and Question Generation as Dual Tasks
• Learning to Ask: Neural Question Generation for Reading Comprehension
• NewsQA: A Machine Comprehension Dataset
• Multiresolution Graph Attention Networks for Relevance Matching
• Neural Question Generation from Text: A Preliminary Study
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Difficulty Controllable Generation of Reading Comprehension Questions
• A Syntactic Approach to Domain-Specific Automatic Question Generation
• Improving Neural Question Generation using Answer Separation
• Sequential Copying Networks

Cited by in corpus (18)

• A Survey of Natural Language Generation
• Graph Neural Networks for Natural Language Processing: A Survey
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Multi-hop Question Generation with Graph Convolutional Network
• A Network Science perspective of Graph Convolutional Networks: A survey
• ProKnow: Process Knowledge for Safety Constrained and Explainable Question Generation for Mental Health Diagnostic Assistance
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
• Accelerating Real-Time Question Answering via Question Generation
• Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data
• Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation
• Summary-Oriented Question Generation for Informational Queries
• Let Me Know What to Ask: Interrogative-Word-Aware Question Generation
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Semantic-Based Self-Critical Training For Question Generation
• Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting
• DORB: Dynamically Optimizing Multiple Rewards with Bandits
• Extended Answer and Uncertainty Aware Neural Question Generation