Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization

Markus Dreyer, Mengwen Liu, Feng Nan, Sandeep Atluri, Sujith Ravi


Abstract
Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documents. In this paper, we analyze the tradeoff between abstractiveness and factuality of generated summaries across multiple datasets and models, using extensive human evaluations of factuality. In our analysis, we visualize the rates of change in factuality as we gradually increase abstractiveness using a decoding constraint, and we observe that, while increased abstractiveness generally leads to a drop in factuality, the rate of factuality decay depends on factors such as the data that the system was trained on. We introduce two datasets with human factuality judgements; one containing 10.2k generated summaries with systematically varied degrees of abstractiveness; the other containing 4.2k summaries from five different summarization models. We propose new factuality metrics that adjust for the degree of abstractiveness, and we use them to compare the abstractiveness-adjusted factuality of previous summarization works, providing baselines for future work.
Anthology ID:
2023.findings-eacl.156
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2089–2105
Language:
URL:
https://aclanthology.org/2023.findings-eacl.156
DOI:
10.18653/v1/2023.findings-eacl.156
Bibkey:
Cite (ACL):
Markus Dreyer, Mengwen Liu, Feng Nan, Sandeep Atluri, and Sujith Ravi. 2023. Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2089–2105, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization (Dreyer et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.findings-eacl.156.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.findings-eacl.156.mp4