Exploring Neural Models for Query-Focused Summarization
This work addresses the problem of enabling user control and personalization in summarization for researchers and practitioners, but it is incremental as it builds on existing datasets and methods.
The paper tackled the lack of comprehensive studies in query-focused summarization by systematically exploring neural approaches, including two-stage and end-to-end models, and achieved state-of-the-art performance with improvements of up to 3.38 ROUGE-1, 3.72 ROUGE-2, and 3.28 ROUGE-L on the QMSum dataset.
Query-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and personalization. While recently released datasets, such as QMSum or AQuaMuSe, facilitate research efforts in QFS, the field lacks a comprehensive study of the broad space of applicable modeling methods. In this paper we conduct a systematic exploration of neural approaches to QFS, considering two general classes of methods: two-stage extractive-abstractive solutions and end-to-end models. Within those categories, we investigate existing models and explore strategies for transfer learning. We also present two modeling extensions that achieve state-of-the-art performance on the QMSum dataset, up to a margin of 3.38 ROUGE-1, 3.72 ROUGE2, and 3.28 ROUGE-L when combined with transfer learning strategies. Results from human evaluation suggest that the best models produce more comprehensive and factually consistent summaries compared to a baseline model. Code and checkpoints are made publicly available: https://github.com/salesforce/query-focused-sum.