Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

Abstract

Query focused summarization (QFS) models aim to generate summaries from source documents that can answer the given query. Most previous work on QFS only considers the query relevance criterion when producing the summary. However, studying the effect of answer relevance in the summary generating process is also important. In this paper, we propose QFS-BART, a model that incorporates the explicit answer relevance of the source documents given the query via a question answering model, to generate coherent and answer-related summaries. Furthermore, our model can take advantage of large pre-trained models which improve the summarization performance significantly. Empirical results on the Debatepedia dataset show that the proposed model achieves the new state-of-the-art performance.

arXiv commentThe two authors contribute equally. Accepted as a short paper in Findings of ACL 2021

References in corpus (21)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Teaching Machines to Read and Comprehend
• A Deep Reinforced Model for Abstractive Summarization
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• End-to-End Open-Domain Question Answering with BERTserini
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Text Summarization with Pretrained Encoders
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Get To The Point: Summarization with Pointer-Generator Networks
• NewsQA: A Machine Comprehension Dataset
• Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
• Bottom-Up Abstractive Summarization
• ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation
• CrossNER: Evaluating Cross-Domain Named Entity Recognition
• Conditional Self-Attention for Query-based Summarization
• AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization
• Query Focused Multi-Document Summarization with Distant Supervision
• CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management
• A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization
• Generating Query Focused Summaries from Query-Free Resources