Self-Repetition in Abstractive Neural Summarizers

Nikita Salkar, Thomas Trikalinos, Byron Wallace, Ani Nenkova

Abstract
We provide a quantitative and qualitative analysis of self-repetition in the output of neural summarizers. We measure self-repetition as the number of n-grams of length four or longer that appear in multiple outputs of the same system. We analyze the behavior of three popular architectures (BART, T5, and Pegasus), fine-tuned on five datasets. In a regression analysis, we find that the three architectures have different propensities for repeating content across output summaries for inputs, with BART being particularly prone to self-repetition. Fine-tuning on more abstractive data, and on data featuring formulaic language is associated with a higher rate of self-repetition. In qualitative analysis, we find systems produce artefacts such as ads and disclaimers unrelated to the content being summarized, as well as formulaic phrases common in the fine-tuning domain. Our approach to corpus-level analysis of self-repetition may help practitioners clean up training data for summarizers and ultimately support methods for minimizing the amount of self-repetition.
Anthology ID:
2022.aacl-short.42
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
341–350
Language:
URL:
https://preview.aclanthology.org/add_missing_videos/2022.aacl-short.42/
DOI:
10.18653/v1/2022.aacl-short.42
Bibkey:
Cite (ACL):
Nikita Salkar, Thomas Trikalinos, Byron Wallace, and Ani Nenkova. 2022. Self-Repetition in Abstractive Neural Summarizers. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 341–350, Online only. Association for Computational Linguistics.
Cite (Informal):
Self-Repetition in Abstractive Neural Summarizers (Salkar et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_missing_videos/2022.aacl-short.42.pdf
PDF Search Fix data