@inproceedings{zeng-etal-2023-extract,
title = "Extract and Attend: Improving Entity Translation in Neural Machine Translation",
author = "Zeng, Zixin and
Wang, Rui and
Leng, Yichong and
Guo, Junliang and
Xie, Shufang and
Tan, Xu and
Qin, Tao and
Liu, Tie-Yan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.107",
doi = "10.18653/v1/2023.findings-acl.107",
pages = "1697--1710",
abstract = "While Neural Machine Translation (NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candidates of source entities are first extracted from a dictionary and then attended to by the NMT model to generate the target sentence. Specifically, the translation candidates are extracted by first detecting the entities in a source sentence and then translating the entities through looking up in a dictionary. Then, the extracted candidates are added as a prefix of the decoder input to be attended to by the decoder when generating the target sentence through self-attention. Experiments conducted on En-Zh and En-Ru demonstrate that the proposed method is effective on improving both the translation accuracy of entities and the overall translation quality, with up to 35{\%} reduction on entity error rate and 0.85 gain on BLEU and 13.8 gain on COMET.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2023-extract">
<titleInfo>
<title>Extract and Attend: Improving Entity Translation in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixin</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichong</namePart>
<namePart type="family">Leng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junliang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shufang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tie-Yan</namePart>
<namePart type="family">Liu</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>Findings of the Association for Computational Linguistics: ACL 2023</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>While Neural Machine Translation (NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candidates of source entities are first extracted from a dictionary and then attended to by the NMT model to generate the target sentence. Specifically, the translation candidates are extracted by first detecting the entities in a source sentence and then translating the entities through looking up in a dictionary. Then, the extracted candidates are added as a prefix of the decoder input to be attended to by the decoder when generating the target sentence through self-attention. Experiments conducted on En-Zh and En-Ru demonstrate that the proposed method is effective on improving both the translation accuracy of entities and the overall translation quality, with up to 35% reduction on entity error rate and 0.85 gain on BLEU and 13.8 gain on COMET.</abstract>
<identifier type="citekey">zeng-etal-2023-extract</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.107</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.107</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1697</start>
<end>1710</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extract and Attend: Improving Entity Translation in Neural Machine Translation
%A Zeng, Zixin
%A Wang, Rui
%A Leng, Yichong
%A Guo, Junliang
%A Xie, Shufang
%A Tan, Xu
%A Qin, Tao
%A Liu, Tie-Yan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zeng-etal-2023-extract
%X While Neural Machine Translation (NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candidates of source entities are first extracted from a dictionary and then attended to by the NMT model to generate the target sentence. Specifically, the translation candidates are extracted by first detecting the entities in a source sentence and then translating the entities through looking up in a dictionary. Then, the extracted candidates are added as a prefix of the decoder input to be attended to by the decoder when generating the target sentence through self-attention. Experiments conducted on En-Zh and En-Ru demonstrate that the proposed method is effective on improving both the translation accuracy of entities and the overall translation quality, with up to 35% reduction on entity error rate and 0.85 gain on BLEU and 13.8 gain on COMET.
%R 10.18653/v1/2023.findings-acl.107
%U https://aclanthology.org/2023.findings-acl.107
%U https://doi.org/10.18653/v1/2023.findings-acl.107
%P 1697-1710
Markdown (Informal)
[Extract and Attend: Improving Entity Translation in Neural Machine Translation](https://aclanthology.org/2023.findings-acl.107) (Zeng et al., Findings 2023)
ACL
- Zixin Zeng, Rui Wang, Yichong Leng, Junliang Guo, Shufang Xie, Xu Tan, Tao Qin, and Tie-Yan Liu. 2023. Extract and Attend: Improving Entity Translation in Neural Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1697–1710, Toronto, Canada. Association for Computational Linguistics.