Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning

Travis Goodwin, Max Savery, Dina Demner-Fushman


Abstract
Automatic summarization research has traditionally focused on providing high quality general-purpose summaries of documents. However, there are many applications which require more specific summaries, such as supporting question answering or topic-based literature discovery. In this paper we study the problem of conditional summarization in which content selection and surface realization are explicitly conditioned on an ad-hoc natural language question or topic description. Because of the difficulty in obtaining sufficient reference summaries to support arbitrary conditional summarization, we explore the use of multi-task fine-tuning (MTFT) on twenty-one natural language tasks to enable zero-shot conditional summarization on five tasks. We present four new summarization datasets, two novel “online” or adaptive task-mixing strategies, and report zero-shot performance using T5 and BART, demonstrating that MTFT can improve zero-shot summarization quality.
Anthology ID:
2020.findings-emnlp.289
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3215–3226
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.289
DOI:
10.18653/v1/2020.findings-emnlp.289
Bibkey:
Cite (ACL):
Travis Goodwin, Max Savery, and Dina Demner-Fushman. 2020. Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3215–3226, Online. Association for Computational Linguistics.
Cite (Informal):
Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning (Goodwin et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.289.pdf
Code
 h4ste/mtft_zsl
Data
BioASQCOPACosmosQAMC-TACOSQuAD