A Joint Model for Question Answering and Question Generation

Abstract

We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents. The proposed model uses a sequence-to-sequence framework that encodes the document and generates a question (answer) given an answer (question). Significant improvement in model performance is observed empirically on the SQuAD corpus, confirming our hypothesis that the model benefits from jointly learning to perform both tasks. We believe the joint model's novelty offers a new perspective on machine comprehension beyond architectural engineering, and serves as a first step towards autonomous information seeking.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Natural Language Processing (almost) from Scratch
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Machine Comprehension Using Match-LSTM and Answer Pointer
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Learning to Ask: Neural Question Generation for Reading Comprehension
• NewsQA: A Machine Comprehension Dataset
• Semi-Supervised QA with Generative Domain-Adaptive Nets

Cited by in corpus (18)

• StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
• Recent Advances in Neural Question Generation
• A Unified Query-based Generative Model for Question Generation and Question Answering
• OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach
• Information Maximizing Visual Question Generation
• Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
• C3VQG: Category Consistent Cyclic Visual Question Generation
• Towards a Better Metric for Evaluating Question Generation Systems
• Title-Guided Encoding for Keyphrase Generation
• Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data
• Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning
• Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints
• Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction
• A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation
• Exploiting Sentence-Level Representations for Passage Ranking
• Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
• Bi-directional Cognitive Thinking Network for Machine Reading Comprehension
• Generating Highly Relevant Questions