@inproceedings{cao-etal-2023-bridging,
title = "Bridging the Domain Gaps in Context Representations for $k$-Nearest Neighbor Neural Machine Translation",
author = "Cao, Zhiwei and
Yang, Baosong and
Lin, Huan and
Wu, Suhang and
Wei, Xiangpeng and
Liu, Dayiheng and
Xie, Jun and
Zhang, Min and
Su, Jinsong",
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.321",
doi = "10.18653/v1/2023.acl-long.321",
pages = "5841--5853",
abstract = "$k$-Nearest neighbor machine translation ($k$NN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it is equipped with a datastore containing vectorized key-value pairs, which are retrieved during inference to benefit translation.However, there often exists a significant gap between upstream and downstream domains, which hurts the datastore retrieval and the final translation quality.To deal with this issue, we propose a novel approach to boost the datastore retrieval of $k$NN-MT by reconstructing the original datastore.Concretely, we design a reviser to revise the key representations, making them better fit for the downstream domain. The reviser is trained using the collected semantically-related key-queries pairs, and optimized by two proposed losses: one is the key-queries semantic distance ensuring each revised key representation is semantically related to its corresponding queries, and the other is an L2-norm loss encouraging revised key representations to effectively retain the knowledge learned by the upstream NMT model. Extensive experiments on domain adaptation tasks demonstrate that our method can effectively boost the datastore retrieval and translation quality of $k$NN-MT.Our code is available at \url{https://github.com/DeepLearnXMU/Revised-knn-mt}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2023-bridging">
<titleInfo>
<title>Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangpeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayiheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</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>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>k-Nearest neighbor machine translation (kNN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it is equipped with a datastore containing vectorized key-value pairs, which are retrieved during inference to benefit translation.However, there often exists a significant gap between upstream and downstream domains, which hurts the datastore retrieval and the final translation quality.To deal with this issue, we propose a novel approach to boost the datastore retrieval of kNN-MT by reconstructing the original datastore.Concretely, we design a reviser to revise the key representations, making them better fit for the downstream domain. The reviser is trained using the collected semantically-related key-queries pairs, and optimized by two proposed losses: one is the key-queries semantic distance ensuring each revised key representation is semantically related to its corresponding queries, and the other is an L2-norm loss encouraging revised key representations to effectively retain the knowledge learned by the upstream NMT model. Extensive experiments on domain adaptation tasks demonstrate that our method can effectively boost the datastore retrieval and translation quality of kNN-MT.Our code is available at https://github.com/DeepLearnXMU/Revised-knn-mt.</abstract>
<identifier type="citekey">cao-etal-2023-bridging</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.321</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.321</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5841</start>
<end>5853</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation
%A Cao, Zhiwei
%A Yang, Baosong
%A Lin, Huan
%A Wu, Suhang
%A Wei, Xiangpeng
%A Liu, Dayiheng
%A Xie, Jun
%A Zhang, Min
%A Su, Jinsong
%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 cao-etal-2023-bridging
%X k-Nearest neighbor machine translation (kNN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it is equipped with a datastore containing vectorized key-value pairs, which are retrieved during inference to benefit translation.However, there often exists a significant gap between upstream and downstream domains, which hurts the datastore retrieval and the final translation quality.To deal with this issue, we propose a novel approach to boost the datastore retrieval of kNN-MT by reconstructing the original datastore.Concretely, we design a reviser to revise the key representations, making them better fit for the downstream domain. The reviser is trained using the collected semantically-related key-queries pairs, and optimized by two proposed losses: one is the key-queries semantic distance ensuring each revised key representation is semantically related to its corresponding queries, and the other is an L2-norm loss encouraging revised key representations to effectively retain the knowledge learned by the upstream NMT model. Extensive experiments on domain adaptation tasks demonstrate that our method can effectively boost the datastore retrieval and translation quality of kNN-MT.Our code is available at https://github.com/DeepLearnXMU/Revised-knn-mt.
%R 10.18653/v1/2023.acl-long.321
%U https://aclanthology.org/2023.acl-long.321
%U https://doi.org/10.18653/v1/2023.acl-long.321
%P 5841-5853
Markdown (Informal)
[Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation](https://aclanthology.org/2023.acl-long.321) (Cao et al., ACL 2023)
ACL
- Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu, Xiangpeng Wei, Dayiheng Liu, Jun Xie, Min Zhang, and Jinsong Su. 2023. Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5841–5853, Toronto, Canada. Association for Computational Linguistics.