Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization

Artidoro Pagnoni, Alex Fabbri, Wojciech Kryscinski, Chien-Sheng Wu


Abstract
In long document controllable summarization, where labeled data is scarce, pretrained models struggle to adapt to the task and effectively respond to user queries. In this paper, we introduce Socratic pretraining, a question-driven, unsupervised pretraining objective specifically designed to improve controllability in summarization tasks. By training a model to generate and answer relevant questions in a given context, Socratic pretraining enables the model to more effectively adhere to user-provided queries and identify relevant content to be summarized. We demonstrate the effectiveness of this approach through extensive experimentation on two summarization domains, short stories and dialogue, and multiple control strategies: keywords, questions, and factoid QA pairs. Our pretraining method relies only on unlabeled documents and a question generation system and outperforms pre-finetuning approaches that use additional supervised data. Furthermore, our results show that Socratic pretraining cuts task-specific labeled data requirements in half, is more faithful to user-provided queries, and achieves state-of-the-art performance on QMSum and SQuALITY.
Anthology ID:
2023.acl-long.713
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12737–12755
Language:
URL:
https://aclanthology.org/2023.acl-long.713
DOI:
10.18653/v1/2023.acl-long.713
Bibkey:
Cite (ACL):
Artidoro Pagnoni, Alex Fabbri, Wojciech Kryscinski, and Chien-Sheng Wu. 2023. Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12737–12755, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization (Pagnoni et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.713.pdf