@inproceedings{wang-etal-2022-efficient,
title = "Efficient Cluster-Based $k$-Nearest-Neighbor Machine Translation",
author = "Wang, Dexin and
Fan, Kai and
Chen, Boxing and
Xiong, Deyi",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.154",
doi = "10.18653/v1/2022.acl-long.154",
pages = "2175--2187",
abstract = "$k$-Nearest-Neighbor Machine Translation ($k$NN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT). It aims to alleviate the performance degradation of advanced MT systems in translating out-of-domain sentences by coordinating with an additional token-level feature-based retrieval module constructed from in-domain data. Previous studies (Khandelwal et al., 2021; Zheng et al., 2021) have already demonstrated that non-parametric NMT is even superior to models fine-tuned on out-of-domain data. In spite of this success, $k$NN retrieval is at the expense of high latency, in particular for large datastores. To make it practical, in this paper, we explore a more efficient $k$NN-MT and propose to use clustering to improve the retrieval efficiency. Concretely, we first propose a cluster-based Compact Network for feature reduction in a contrastive learning manner to compress context features into 90+{\%} lower dimensional vectors. We then suggest a cluster-based pruning solution to filter out 10{\%} 40{\%} redundant nodes in large datastores while retaining translation quality. Our proposed methods achieve better or comparable performance while reducing up to 57{\%} inference latency against the advanced non-parametric MT model on several machine translation benchmarks. Experimental results indicate that the proposed methods maintain the most useful information of the original datastore and the Compact Network shows good generalization on unseen domains. Codes are available at \url{https://github.com/tjunlp-lab/PCKMT}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-efficient">
<titleInfo>
<title>Efficient Cluster-Based k-Nearest-Neighbor Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dexin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</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>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT). It aims to alleviate the performance degradation of advanced MT systems in translating out-of-domain sentences by coordinating with an additional token-level feature-based retrieval module constructed from in-domain data. Previous studies (Khandelwal et al., 2021; Zheng et al., 2021) have already demonstrated that non-parametric NMT is even superior to models fine-tuned on out-of-domain data. In spite of this success, kNN retrieval is at the expense of high latency, in particular for large datastores. To make it practical, in this paper, we explore a more efficient kNN-MT and propose to use clustering to improve the retrieval efficiency. Concretely, we first propose a cluster-based Compact Network for feature reduction in a contrastive learning manner to compress context features into 90+% lower dimensional vectors. We then suggest a cluster-based pruning solution to filter out 10% 40% redundant nodes in large datastores while retaining translation quality. Our proposed methods achieve better or comparable performance while reducing up to 57% inference latency against the advanced non-parametric MT model on several machine translation benchmarks. Experimental results indicate that the proposed methods maintain the most useful information of the original datastore and the Compact Network shows good generalization on unseen domains. Codes are available at https://github.com/tjunlp-lab/PCKMT.</abstract>
<identifier type="citekey">wang-etal-2022-efficient</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.154</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.154</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2175</start>
<end>2187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Cluster-Based k-Nearest-Neighbor Machine Translation
%A Wang, Dexin
%A Fan, Kai
%A Chen, Boxing
%A Xiong, Deyi
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F wang-etal-2022-efficient
%X k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT). It aims to alleviate the performance degradation of advanced MT systems in translating out-of-domain sentences by coordinating with an additional token-level feature-based retrieval module constructed from in-domain data. Previous studies (Khandelwal et al., 2021; Zheng et al., 2021) have already demonstrated that non-parametric NMT is even superior to models fine-tuned on out-of-domain data. In spite of this success, kNN retrieval is at the expense of high latency, in particular for large datastores. To make it practical, in this paper, we explore a more efficient kNN-MT and propose to use clustering to improve the retrieval efficiency. Concretely, we first propose a cluster-based Compact Network for feature reduction in a contrastive learning manner to compress context features into 90+% lower dimensional vectors. We then suggest a cluster-based pruning solution to filter out 10% 40% redundant nodes in large datastores while retaining translation quality. Our proposed methods achieve better or comparable performance while reducing up to 57% inference latency against the advanced non-parametric MT model on several machine translation benchmarks. Experimental results indicate that the proposed methods maintain the most useful information of the original datastore and the Compact Network shows good generalization on unseen domains. Codes are available at https://github.com/tjunlp-lab/PCKMT.
%R 10.18653/v1/2022.acl-long.154
%U https://aclanthology.org/2022.acl-long.154
%U https://doi.org/10.18653/v1/2022.acl-long.154
%P 2175-2187
Markdown (Informal)
[Efficient Cluster-Based k-Nearest-Neighbor Machine Translation](https://aclanthology.org/2022.acl-long.154) (Wang et al., ACL 2022)
ACL
- Dexin Wang, Kai Fan, Boxing Chen, and Deyi Xiong. 2022. Efficient Cluster-Based k-Nearest-Neighbor Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2175–2187, Dublin, Ireland. Association for Computational Linguistics.