@inproceedings{minh-cong-etal-2022-simple,
title = "A Simple and Fast Strategy for Handling Rare Words in Neural Machine Translation",
author = "Minh-Cong, Nguyen-Hoang and
Ngo, Vinh Thi and
Nguyen, Van Vinh",
editor = "Hanqi, Yan and
Zonghan, Yang and
Ruder, Sebastian and
Xiaojun, Wan",
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: Student Research Workshop",
month = nov,
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-srw.6",
doi = "10.18653/v1/2022.aacl-srw.6",
pages = "40--46",
abstract = "Neural Machine Translation (NMT) has currently obtained state-of-the-art in machine translation systems. However, dealing with rare words is still a big challenge in translation systems. The rare words are often translated using a manual dictionary or copied from the source to the target with original words. In this paper, we propose a simple and fast strategy for integrating constraints during the training and decoding process to improve the translation of rare words. The effectiveness of our proposal is demonstrated in both high and low-resource translation tasks, including the language pairs: English → Vietnamese, Chinese → Vietnamese, Khmer → Vietnamese, and Lao → Vietnamese. We show the improvements of up to +1.8 BLEU scores over the baseline systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="minh-cong-etal-2022-simple">
<titleInfo>
<title>A Simple and Fast Strategy for Handling Rare Words in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nguyen-Hoang</namePart>
<namePart type="family">Minh-Cong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinh</namePart>
<namePart type="given">Thi</namePart>
<namePart type="family">Ngo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Van</namePart>
<namePart type="given">Vinh</namePart>
<namePart type="family">Nguyen</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: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Hanqi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zonghan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wan</namePart>
<namePart type="family">Xiaojun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) has currently obtained state-of-the-art in machine translation systems. However, dealing with rare words is still a big challenge in translation systems. The rare words are often translated using a manual dictionary or copied from the source to the target with original words. In this paper, we propose a simple and fast strategy for integrating constraints during the training and decoding process to improve the translation of rare words. The effectiveness of our proposal is demonstrated in both high and low-resource translation tasks, including the language pairs: English → Vietnamese, Chinese → Vietnamese, Khmer → Vietnamese, and Lao → Vietnamese. We show the improvements of up to +1.8 BLEU scores over the baseline systems.</abstract>
<identifier type="citekey">minh-cong-etal-2022-simple</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-srw.6</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-srw.6</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>40</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple and Fast Strategy for Handling Rare Words in Neural Machine Translation
%A Minh-Cong, Nguyen-Hoang
%A Ngo, Vinh Thi
%A Nguyen, Van Vinh
%Y Hanqi, Yan
%Y Zonghan, Yang
%Y Ruder, Sebastian
%Y Xiaojun, Wan
%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: Student Research Workshop
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online
%F minh-cong-etal-2022-simple
%X Neural Machine Translation (NMT) has currently obtained state-of-the-art in machine translation systems. However, dealing with rare words is still a big challenge in translation systems. The rare words are often translated using a manual dictionary or copied from the source to the target with original words. In this paper, we propose a simple and fast strategy for integrating constraints during the training and decoding process to improve the translation of rare words. The effectiveness of our proposal is demonstrated in both high and low-resource translation tasks, including the language pairs: English → Vietnamese, Chinese → Vietnamese, Khmer → Vietnamese, and Lao → Vietnamese. We show the improvements of up to +1.8 BLEU scores over the baseline systems.
%R 10.18653/v1/2022.aacl-srw.6
%U https://aclanthology.org/2022.aacl-srw.6
%U https://doi.org/10.18653/v1/2022.aacl-srw.6
%P 40-46
Markdown (Informal)
[A Simple and Fast Strategy for Handling Rare Words in Neural Machine Translation](https://aclanthology.org/2022.aacl-srw.6) (Minh-Cong et al., AACL-IJCNLP 2022)
ACL
- Nguyen-Hoang Minh-Cong, Vinh Thi Ngo, and Van Vinh Nguyen. 2022. A Simple and Fast Strategy for Handling Rare Words in Neural Machine Translation. 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: Student Research Workshop, pages 40–46, Online. Association for Computational Linguistics.