A Unified Query-based Generative Model for Question Generation and Question Answering

Abstract

We propose a query-based generative model for solving both tasks of question generation (QG) and question an- swering (QA). The model follows the classic encoder- decoder framework. The encoder takes a passage and a query as input then performs query understanding by matching the query with the passage from multiple per- spectives. The decoder is an attention-based Long Short Term Memory (LSTM) model with copy and coverage mechanisms. In the QG task, a question is generated from the system given the passage and the target answer, whereas in the QA task, the answer is generated given the question and the passage. During the training stage, we leverage a policy-gradient reinforcement learning algorithm to overcome exposure bias, a major prob- lem resulted from sequence learning with cross-entropy loss. For the QG task, our experiments show higher per- formances than the state-of-the-art results. When used as additional training data, the automatically generated questions even improve the performance of a strong ex- tractive QA system. In addition, our model shows bet- ter performance than the state-of-the-art baselines of the generative QA task.

References in corpus (25)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Bidirectional Attention Flow for Machine Comprehension
• A Deep Reinforced Model for Abstractive Summarization
• Dynamic Coattention Networks For Question Answering
• Machine Comprehension Using Match-LSTM and Answer Pointer
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Question Answering and Question Generation as Dual Tasks
• Modeling Coverage for Neural Machine Translation
• Learning Recurrent Span Representations for Extractive Question Answering
• Multi-Perspective Context Matching for Machine Comprehension
• Learning to Ask: Neural Question Generation for Reading Comprehension
• A Joint Model for Question Answering and Question Generation
• Pointing the Unknown Words
• S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Neural Question Generation from Text: A Preliminary Study
• Neural Models for Key Phrase Detection and Question Generation
• Neural Generative Question Answering
• Semi-Supervised QA with Generative Domain-Adaptive Nets

Cited by in corpus (13)

• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
• OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach
• Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
• TWEETQA: A Social Media Focused Question Answering Dataset
• Title-Guided Encoding for Keyphrase Generation
• Let's Ask Again: Refine Network for Automatic Question Generation
• DORB: Dynamically Optimizing Multiple Rewards with Bandits
• Extended Answer and Uncertainty Aware Neural Question Generation
• Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism
• Conditionally Learn to Pay Attention for Sequential Visual Task