@inproceedings{wang-etal-2022-adversarially,
title = "Adversarially Improving {NMT} Robustness to {ASR} Errors with Confusion Sets",
author = "Wang, Shuaibo and
Chen, Yufeng and
Zhang, Songming and
Xiong, Deyi and
Xu, Jinan",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "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 = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.28",
doi = "10.18653/v1/2022.aacl-short.28",
pages = "221--227",
abstract = "Neural machine translation (NMT) models are known to be fragile to noisy inputs from automatic speech recognition (ASR) systems. Existing methods are usually tailored for robustness against only homophone errors which account for a small portion of realistic ASR errors. In this paper, we propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarial training for NMT models. Specifically, an adversarial example is generated from the perspective of acoustic relations instead of the traditional uniform or unigram sampling from the confusion sets. Experiments on different test sets with hand-crafted and real-world noise demonstrate the effectiveness of our method over previous methods. Moreover, our approach can achieve improvements on the clean test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-adversarially">
<titleInfo>
<title>Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuaibo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>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)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural machine translation (NMT) models are known to be fragile to noisy inputs from automatic speech recognition (ASR) systems. Existing methods are usually tailored for robustness against only homophone errors which account for a small portion of realistic ASR errors. In this paper, we propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarial training for NMT models. Specifically, an adversarial example is generated from the perspective of acoustic relations instead of the traditional uniform or unigram sampling from the confusion sets. Experiments on different test sets with hand-crafted and real-world noise demonstrate the effectiveness of our method over previous methods. Moreover, our approach can achieve improvements on the clean test set.</abstract>
<identifier type="citekey">wang-etal-2022-adversarially</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-short.28</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.28</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>221</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets
%A Wang, Shuaibo
%A Chen, Yufeng
%A Zhang, Songming
%A Xiong, Deyi
%A Xu, Jinan
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S 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)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F wang-etal-2022-adversarially
%X Neural machine translation (NMT) models are known to be fragile to noisy inputs from automatic speech recognition (ASR) systems. Existing methods are usually tailored for robustness against only homophone errors which account for a small portion of realistic ASR errors. In this paper, we propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarial training for NMT models. Specifically, an adversarial example is generated from the perspective of acoustic relations instead of the traditional uniform or unigram sampling from the confusion sets. Experiments on different test sets with hand-crafted and real-world noise demonstrate the effectiveness of our method over previous methods. Moreover, our approach can achieve improvements on the clean test set.
%R 10.18653/v1/2022.aacl-short.28
%U https://aclanthology.org/2022.aacl-short.28
%U https://doi.org/10.18653/v1/2022.aacl-short.28
%P 221-227
Markdown (Informal)
[Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets](https://aclanthology.org/2022.aacl-short.28) (Wang et al., AACL-IJCNLP 2022)
ACL
- Shuaibo Wang, Yufeng Chen, Songming Zhang, Deyi Xiong, and Jinan Xu. 2022. Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets. 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 221–227, Online only. Association for Computational Linguistics.