Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model

2019/10/19 by Yu Chen, Chen, Yu, Lingfei Wu +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1910.08832

openalex publication_date 2019/10/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Natural question generation (QG) aims to generate questions from a passage and an answer. In this paper, we propose a novel reinforcement learning (RL) based graph-to-sequence (Graph2Seq) model for QG. Our model consists of a Graph2Seq generator where a novel Bidirectional Gated Graph Neural Network is proposed to embed the passage, and a hybrid evaluator with a mixed objective combining both cross-entropy and RL losses to ensure the generation of syntactically and semantically valid text. The proposed model outperforms previous state-of-the-art methods by a large margin on the SQuAD dataset.

Citations

• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Adam: A Method for Stochastic Optimization
• Variational Dropout and the Local Reparameterization Trick
• Long Short-Term Memory
• Sequence Level Training with Recurrent Neural Networks
• Gated Graph Sequence Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Learning to Ask: Neural Question Generation for Reading Comprehension
• A Deep Reinforced Model for Abstractive Summarization
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
• SQL-to-Text Generation with Graph-to-Sequence Model
• Get To The Point: Summarization with Pointer-Generator Networks
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension

Cited by

• A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation

Related

• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Machine Comprehension by Text-to-Text Neural Question Generation
• Graph Guided Question Answer Generation for Procedural Question-Answering
• Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text
• A Unified Query-based Generative Model for Question Generation and Question Answering