Improving the Robustness of Summarization Systems with Dual Augmentation

Xiuying Chen, Guodong Long, Chongyang Tao, Mingzhe Li, Xin Gao, Chengqi Zhang, Xiangliang Zhang


Abstract
A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models’ robustness against perturbations including word-level synonym substitution and noise. To create semantic-consistent substitutes, we propose a SummAttacker, which is an efficient approach to generating adversarial samples based on pre-trained language models. Experimental results show that state-of-the-art summarization models have a significant decrease in performance on adversarial and noisy test sets. Next, we analyze the vulnerability of the summarization systems and explore improving the robustness by data augmentation. Specifically, the first vulnerability factor we found is the low diversity of the training inputs. Correspondingly, we expose the encoder to more diverse cases created by SummAttacker in the input space. The second factor is the vulnerability of the decoder, and we propose an augmentation in the latent space of the decoder to improve its robustness. Concretely, we create virtual cases by manifold softmixing two decoder hidden states of similar semantic meanings. Experimental results on Gigaword and CNN/DM datasets demonstrate that our approach achieves significant improvements over strong baselines and exhibits higher robustness on noisy, attacked, and clean datasets
Anthology ID:
2023.acl-long.378
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6846–6857
Language:
URL:
https://aclanthology.org/2023.acl-long.378
DOI:
10.18653/v1/2023.acl-long.378
Bibkey:
Cite (ACL):
Xiuying Chen, Guodong Long, Chongyang Tao, Mingzhe Li, Xin Gao, Chengqi Zhang, and Xiangliang Zhang. 2023. Improving the Robustness of Summarization Systems with Dual Augmentation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6846–6857, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Improving the Robustness of Summarization Systems with Dual Augmentation (Chen et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.378.pdf
Video:
 https://aclanthology.org/2023.acl-long.378.mp4