A Joint Model for Question Answering and Question Generation

2017/06/05 by Tong Wang, Xingdi Yuan, Wang, Tong +3 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Expert finding and Q&A systems #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1706.01450

openalex publication_date 2017/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Neural Machine Translation by Jointly Learning to Align and Translate

Cited by

• Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints

Related

• Machine Comprehension by Text-to-Text Neural Question Generation
• A Generative Approach to Question Answering
• Multi-Task Learning with Language Modeling for Question Generation
• Dual Ask-Answer Network for Machine Reading Comprehension
• A Unified Query-based Generative Model for Question Generation and Question Answering