Planning with Learned Entity Prompts for Abstractive Summarization
Shashi Narayan, Yao Zhao, Joshua Maynez, Gonçalo Simões, Vitaly Nikolaev, Ryan McDonald
Abstract
We introduce a simple but flexible mechanism to learn an intermediate plan to ground the generation of abstractive summaries. Specifically, we prepend (or prompt) target summaries with entity chains—ordered sequences of entities mentioned in the summary. Transformer-based sequence-to-sequence models are then trained to generate the entity chain and then continue generating the summary conditioned on the entity chain and the input. We experimented with both pretraining and finetuning with this content planning objective. When evaluated on CNN/DailyMail, XSum, SAMSum, and BillSum, we demonstrate empirically that the grounded generation with the planning objective improves entity specificity and planning in summaries for all datasets, and achieves state-of-the-art performance on XSum and SAMSum in terms of rouge. Moreover, we demonstrate empirically that planning with entity chains provides a mechanism to control hallucinations in abstractive summaries. By prompting the decoder with a modified content plan that drops hallucinated entities, we outperform state-of-the-art approaches for faithfulness when evaluated automatically and by humans.- Anthology ID:
- 2021.tacl-1.88
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 9
- Month:
- Year:
- 2021
- Address:
- Cambridge, MA
- Editors:
- Brian Roark, Ani Nenkova
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 1475–1492
- Language:
- URL:
- https://aclanthology.org/2021.tacl-1.88
- DOI:
- 10.1162/tacl_a_00438
- Cite (ACL):
- Shashi Narayan, Yao Zhao, Joshua Maynez, Gonçalo Simões, Vitaly Nikolaev, and Ryan McDonald. 2021. Planning with Learned Entity Prompts for Abstractive Summarization. Transactions of the Association for Computational Linguistics, 9:1475–1492.
- Cite (Informal):
- Planning with Learned Entity Prompts for Abstractive Summarization (Narayan et al., TACL 2021)
- PDF:
- https://preview.aclanthology.org/landing_page/2021.tacl-1.88.pdf