Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

TL;DR

This paper introduces QFS-BART, a query-focused summarization model that incorporates answer relevance through a question answering component, significantly improving answer-related summary quality using large pre-trained models.

Contribution

The paper presents a novel QFS model that explicitly integrates answer relevance via question answering, enhancing summarization performance with large pre-trained models.

Findings

Achieves state-of-the-art results on Debatepedia dataset.

Effectively incorporates answer relevance into query-focused summarization.

Utilizes large pre-trained models to boost performance.

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.