@inproceedings{fu-etal-2023-enabling,
title = "Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations",
author = "Fu, Chengpeng and
Feng, Xiaocheng and
Huang, Yichong and
Huo, Wenshuai and
Wang, Hui and
Qin, Bing and
Liu, Ting",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.839/",
doi = "10.18653/v1/2023.findings-emnlp.839",
pages = "12608--12618",
abstract = "Unsupervised neural machine translation has recently made remarkable strides, achieving impressive results with the exclusive use of monolingual corpora. Nonetheless, these methods still exhibit fundamental flaws, such as confusing similar words. A straightforward remedy to rectify this drawback is to employ bilingual dictionaries, however, high-quality bilingual dictionaries can be costly to obtain. To overcome this limitation, we propose a method that incorporates images at the word level to augment the lexical mappings. Specifically, our method inserts visual representations into the model, modifying the corresponding embedding layer information. Besides, a visible matrix is adopted to isolate the impact of images on other unrelated words. Experiments on the Multi30k dataset with over 300,000 self-collected images validate the effectiveness in generating more accurate word translation, achieving an improvement of up to $+$2.81 BLEU score, which is comparable or even superior to using bilingual dictionaries."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2023-enabling">
<titleInfo>
<title>Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengpeng</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaocheng</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenshuai</namePart>
<namePart type="family">Huo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised neural machine translation has recently made remarkable strides, achieving impressive results with the exclusive use of monolingual corpora. Nonetheless, these methods still exhibit fundamental flaws, such as confusing similar words. A straightforward remedy to rectify this drawback is to employ bilingual dictionaries, however, high-quality bilingual dictionaries can be costly to obtain. To overcome this limitation, we propose a method that incorporates images at the word level to augment the lexical mappings. Specifically, our method inserts visual representations into the model, modifying the corresponding embedding layer information. Besides, a visible matrix is adopted to isolate the impact of images on other unrelated words. Experiments on the Multi30k dataset with over 300,000 self-collected images validate the effectiveness in generating more accurate word translation, achieving an improvement of up to +2.81 BLEU score, which is comparable or even superior to using bilingual dictionaries.</abstract>
<identifier type="citekey">fu-etal-2023-enabling</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.839</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.839/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12608</start>
<end>12618</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations
%A Fu, Chengpeng
%A Feng, Xiaocheng
%A Huang, Yichong
%A Huo, Wenshuai
%A Wang, Hui
%A Qin, Bing
%A Liu, Ting
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F fu-etal-2023-enabling
%X Unsupervised neural machine translation has recently made remarkable strides, achieving impressive results with the exclusive use of monolingual corpora. Nonetheless, these methods still exhibit fundamental flaws, such as confusing similar words. A straightforward remedy to rectify this drawback is to employ bilingual dictionaries, however, high-quality bilingual dictionaries can be costly to obtain. To overcome this limitation, we propose a method that incorporates images at the word level to augment the lexical mappings. Specifically, our method inserts visual representations into the model, modifying the corresponding embedding layer information. Besides, a visible matrix is adopted to isolate the impact of images on other unrelated words. Experiments on the Multi30k dataset with over 300,000 self-collected images validate the effectiveness in generating more accurate word translation, achieving an improvement of up to +2.81 BLEU score, which is comparable or even superior to using bilingual dictionaries.
%R 10.18653/v1/2023.findings-emnlp.839
%U https://aclanthology.org/2023.findings-emnlp.839/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.839
%P 12608-12618
Markdown (Informal)
[Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations](https://aclanthology.org/2023.findings-emnlp.839/) (Fu et al., Findings 2023)
ACL