Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge

TL;DR

This paper introduces a two-stage, knowledge-enhanced framework for query-focused meeting summarization that improves relevance and faithfulness of summaries, achieving state-of-the-art results on the QMSum dataset.

Contribution

The paper presents a novel two-stage framework that incorporates knowledge-aware scoring and query-relevant knowledge for improved QFMS performance.

Findings

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

Effectively improves relevance of extracted segments.

Generates more faithful and relevant summaries.

Abstract

Query-Focused Meeting Summarization (QFMS) aims to generate a summary of a given meeting transcript conditioned upon a query. The main challenges for QFMS are the long input text length and sparse query-relevant information in the meeting transcript. In this paper, we propose a knowledge-enhanced two-stage framework called Knowledge-Aware Summarizer (KAS) to tackle the challenges. In the first stage, we introduce knowledge-aware scores to improve the query-relevant segment extraction. In the second stage, we incorporate query-relevant knowledge in the summary generation. Experimental results on the QMSum dataset show that our approach achieves state-of-the-art performance. Further analysis proves the competency of our methods in generating relevant and faithful summaries.