CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability

Yixi Ding, Yanxia Qin, Qian Liu, Min-Yen Kan


Abstract
We present a novel toolkit for controlled summarization of scientific documents, designed for the specific needs of the scientific community. Our system generates summaries based on user preferences, adjusting key attributes specifically of length and keyword inclusion. A distinguishing feature is its ability to manage multiple attributes concurrently, demonstrating Compositional Controllability for Scientific Summarization (CocoSciSum). Benchmarked against the strong Flan-T5 baseline, CocoSciSum exhibits superior performance on both the quality of summaries generated and the control over single and multiple attributes. Moreover, CocoSciSum is a user-centric toolkit, supporting user preferences expressed in natural language instructions, and accommodating diverse input document formats. CocoSciSum is available on GitHub (https://github.com/WING-NUS/SciAssist/tree/CocoSciSum) with an introduction video (https://youtu.be/YC1YDeEjAbQ).
Anthology ID:
2023.emnlp-demo.47
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
December
Year:
2023
Address:
Singapore
Editors:
Yansong Feng, Els Lefever
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
518–526
Language:
URL:
https://aclanthology.org/2023.emnlp-demo.47
DOI:
10.18653/v1/2023.emnlp-demo.47
Bibkey:
Cite (ACL):
Yixi Ding, Yanxia Qin, Qian Liu, and Min-Yen Kan. 2023. CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 518–526, Singapore. Association for Computational Linguistics.
Cite (Informal):
CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability (Ding et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-demo.47.pdf
Video:
 https://aclanthology.org/2023.emnlp-demo.47.mp4