Multi-style Generative Reading Comprehension

Abstract

This study tackles generative reading comprehension (RC), which consists of answering questions based on textual evidence and natural language generation (NLG). We propose a multi-style abstractive summarization model for question answering, called Masque. The proposed model has two key characteristics. First, unlike most studies on RC that have focused on extracting an answer span from the provided passages, our model instead focuses on generating a summary from the question and multiple passages. This serves to cover various answer styles required for real-world applications. Second, whereas previous studies built a specific model for each answer style because of the difficulty of acquiring one general model, our approach learns multi-style answers within a model to improve the NLG capability for all styles involved. This also enables our model to give an answer in the target style. Experiments show that our model achieves state-of-the-art performance on the Q&A task and the Q&A + NLG task of MS MARCO 2.1 and the summary task of NarrativeQA. We observe that the transfer of the style-independent NLG capability to the target style is the key to its success.

Accepted as a long paper at ACL 2019

References in corpus (9)

• Bidirectional Attention Flow for Machine Comprehension
• Layer Normalization
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Learning and Evaluating General Linguistic Intelligence
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• Densely Connected Attention Propagation for Reading Comprehension
• Bottom-Up Abstractive Summarization
• U-Net: Machine Reading Comprehension with Unanswerable Questions
• Query-Based Abstractive Summarization Using Neural Networks

Cited by in corpus (7)

• Code Structure Guided Transformer for Source Code Summarization
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
• Frustratingly Hard Evidence Retrieval for QA Over Books
• A Study of the Tasks and Models in Machine Reading Comprehension
• Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study
• Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce