QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

TL;DR

QMSum introduces a new benchmark dataset for query-based multi-domain meeting summarization, highlighting the challenges of summarizing long meetings across various topics and user needs.

Contribution

The paper defines a novel query-based multi-domain meeting summarization task and provides the QMSum benchmark dataset with 1,808 query-summary pairs across 232 meetings.

Findings

QMSum dataset reveals significant challenges in long meeting summarization.

Locate-then-summarize method evaluated on QMSum shows promising results.

Strong baselines still struggle with the complexity of multi-domain meeting summarization.

Abstract

Meetings are a key component of human collaboration. As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed. However, it is hard to create a single short summary that covers all the content of a long meeting involving multiple people and topics. In order to satisfy the needs of different types of users, we define a new query-based multi-domain meeting summarization task, where models have to select and summarize relevant spans of meetings in response to a query, and we introduce QMSum, a new benchmark for this task. QMSum consists of 1,808 query-summary pairs over 232 meetings in multiple domains. Besides, we investigate a locate-then-summarize method and evaluate a set of strong summarization baselines on the task. Experimental results and manual analysis reveal that QMSum presents significant challenges in long meeting summarization for future research. Dataset is available at \url{https://github.com/Yale-LILY/QMSum}.