MACSum: Controllable Summarization with Mixed Attributes

Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, Rui Zhang


Abstract
Controllable summarization allows users to generate customized summaries with specified attributes. However, due to the lack of designated annotations of controlled summaries, existing work has to craft pseudo datasets by adapting generic summarization benchmarks. Furthermore, most research focuses on controlling single attributes individually (e.g., a short summary or a highly abstractive summary) rather than controlling a mix of attributes together (e.g., a short and highly abstractive summary). In this paper, we propose MACSum, the first human-annotated summarization dataset for controlling mixed attributes. It contains source texts from two domains, news articles and dialogues, with human-annotated summaries controlled by five designed attributes (Length, Extractiveness, Specificity, Topic, and Speaker). We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning. Results and analysis demonstrate that hard prompt models yield the best performance on most metrics and human evaluations. However, mixed-attribute control is still challenging for summarization tasks. Our dataset and code are available at https://github.com/psunlpgroup/MACSum.
Anthology ID:
2023.tacl-1.46
Volume:
Transactions of the Association for Computational Linguistics, Volume 11
Month:
Year:
2023
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
787–803
Language:
URL:
https://aclanthology.org/2023.tacl-1.46
DOI:
10.1162/tacl_a_00575
Bibkey:
Cite (ACL):
Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, and Rui Zhang. 2023. MACSum: Controllable Summarization with Mixed Attributes. Transactions of the Association for Computational Linguistics, 11:787–803.
Cite (Informal):
MACSum: Controllable Summarization with Mixed Attributes (Zhang et al., TACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.tacl-1.46.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2023.tacl-1.46.mp4