@inproceedings{chen-etal-2023-improving-robustness,
title = "Improving the Robustness of Summarization Systems with Dual Augmentation",
author = "Chen, Xiuying and
Long, Guodong and
Tao, Chongyang and
Li, Mingzhe and
Gao, Xin and
Zhang, Chengqi and
Zhang, Xiangliang",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.378",
doi = "10.18653/v1/2023.acl-long.378",
pages = "6846--6857",
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",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-improving-robustness">
<titleInfo>
<title>Improving the Robustness of Summarization Systems with Dual Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiuying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongyang</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingzhe</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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</abstract>
<identifier type="citekey">chen-etal-2023-improving-robustness</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.378</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.378</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6846</start>
<end>6857</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving the Robustness of Summarization Systems with Dual Augmentation
%A Chen, Xiuying
%A Long, Guodong
%A Tao, Chongyang
%A Li, Mingzhe
%A Gao, Xin
%A Zhang, Chengqi
%A Zhang, Xiangliang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-improving-robustness
%X 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
%R 10.18653/v1/2023.acl-long.378
%U https://aclanthology.org/2023.acl-long.378
%U https://doi.org/10.18653/v1/2023.acl-long.378
%P 6846-6857
Markdown (Informal)
[Improving the Robustness of Summarization Systems with Dual Augmentation](https://aclanthology.org/2023.acl-long.378) (Chen et al., ACL 2023)
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.