@inproceedings{jiang-etal-2022-towards,
title = "Towards Robust k-Nearest-Neighbor Machine Translation",
author = "Jiang, Hui and
Lu, Ziyao and
Meng, Fandong and
Zhou, Chulun and
Zhou, Jie and
Huang, Degen and
Su, Jinsong",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.367",
doi = "10.18653/v1/2022.emnlp-main.367",
pages = "5468--5477",
abstract = "k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years. Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT model. However, the underlying retrieved noisy pairs will dramatically deteriorate the model performance. In this paper, we conduct a preliminary study and find that this problem results from not fully exploiting the prediction of the NMT model. To alleviate the impact of noise, we propose a confidence-enhanced kNN-MT model with robust training. Concretely, we introduce the NMT confidence to refine the modeling of two important components of kNN-MT: kNN distribution and the interpolation weight. Meanwhile we inject two types of perturbations into the retrieved pairs for robust training. Experimental results on four benchmark datasets demonstrate that our model not only achieves significant improvements over current kNN-MT models, but also exhibits better robustness. Our code is available at \url{https://github.com/DeepLearnXMU/Robust-knn-mt}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2022-towards">
<titleInfo>
<title>Towards Robust k-Nearest-Neighbor Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyao</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Degen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinsong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years. Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT model. However, the underlying retrieved noisy pairs will dramatically deteriorate the model performance. In this paper, we conduct a preliminary study and find that this problem results from not fully exploiting the prediction of the NMT model. To alleviate the impact of noise, we propose a confidence-enhanced kNN-MT model with robust training. Concretely, we introduce the NMT confidence to refine the modeling of two important components of kNN-MT: kNN distribution and the interpolation weight. Meanwhile we inject two types of perturbations into the retrieved pairs for robust training. Experimental results on four benchmark datasets demonstrate that our model not only achieves significant improvements over current kNN-MT models, but also exhibits better robustness. Our code is available at https://github.com/DeepLearnXMU/Robust-knn-mt.</abstract>
<identifier type="citekey">jiang-etal-2022-towards</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.367</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.367</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5468</start>
<end>5477</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Robust k-Nearest-Neighbor Machine Translation
%A Jiang, Hui
%A Lu, Ziyao
%A Meng, Fandong
%A Zhou, Chulun
%A Zhou, Jie
%A Huang, Degen
%A Su, Jinsong
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F jiang-etal-2022-towards
%X k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years. Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT model. However, the underlying retrieved noisy pairs will dramatically deteriorate the model performance. In this paper, we conduct a preliminary study and find that this problem results from not fully exploiting the prediction of the NMT model. To alleviate the impact of noise, we propose a confidence-enhanced kNN-MT model with robust training. Concretely, we introduce the NMT confidence to refine the modeling of two important components of kNN-MT: kNN distribution and the interpolation weight. Meanwhile we inject two types of perturbations into the retrieved pairs for robust training. Experimental results on four benchmark datasets demonstrate that our model not only achieves significant improvements over current kNN-MT models, but also exhibits better robustness. Our code is available at https://github.com/DeepLearnXMU/Robust-knn-mt.
%R 10.18653/v1/2022.emnlp-main.367
%U https://aclanthology.org/2022.emnlp-main.367
%U https://doi.org/10.18653/v1/2022.emnlp-main.367
%P 5468-5477
Markdown (Informal)
[Towards Robust k-Nearest-Neighbor Machine Translation](https://aclanthology.org/2022.emnlp-main.367) (Jiang et al., EMNLP 2022)
ACL
- Hui Jiang, Ziyao Lu, Fandong Meng, Chulun Zhou, Jie Zhou, Degen Huang, and Jinsong Su. 2022. Towards Robust k-Nearest-Neighbor Machine Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5468–5477, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.