UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor

Shangqing Tu, Jifan Yu, Fangwei Zhu, Juanzi Li, Lei Hou, Jian-Yun Nie


Abstract
Multi-Document Summarization (MDS) commonly employs the 2-stage extract-then-abstract paradigm, which first extracts a relatively short meta-document, then feeds it into the deep neural networks to generate an abstract. Previous work usually takes the ROUGE score as the label for training a scoring model to evaluate source documents. However, the trained scoring model is prone to under-fitting for low-resource settings, as it relies on the training data. To extract documents effectively, we construct prompting templates that invoke the underlying knowledge in Pre-trained Language Model (PLM) to calculate the document and keyword’s perplexity, which can assess the document’s semantic salience. Our unsupervised approach can be applied as a plug-in to boost other metrics for evaluating a document’s salience, thus improving the subsequent abstract generation. We get positive results on 2 MDS datasets, 2 data settings, and 2 abstractive backbone models, showing our method’s effectiveness. Our code is available at https://github.com/THU-KEG/UPER
Anthology ID:
2022.coling-1.550
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6315–6326
Language:
URL:
https://aclanthology.org/2022.coling-1.550
DOI:
Bibkey:
Cite (ACL):
Shangqing Tu, Jifan Yu, Fangwei Zhu, Juanzi Li, Lei Hou, and Jian-Yun Nie. 2022. UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6315–6326, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor (Tu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.550.pdf
Code
 thu-keg/uper
Data
WCEPWikiCatSumWikiSum