@inproceedings{tamura-etal-2020-tmu,
title = "{TMU} {J}apanese-{E}nglish Multimodal Machine Translation System for {WAT} 2020",
author = "Tamura, Hiroto and
Hirasawa, Tosho and
Kaneko, Masahiro and
Komachi, Mamoru",
editor = "Nakazawa, Toshiaki and
Nakayama, Hideki and
Ding, Chenchen and
Dabre, Raj and
Kunchukuttan, Anoop and
Pa, Win Pa and
Bojar, Ond{\v{r}}ej and
Parida, Shantipriya and
Goto, Isao and
Mino, Hidaya and
Manabe, Hiroshi and
Sudoh, Katsuhito and
Kurohashi, Sadao and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 7th Workshop on Asian Translation",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wat-1.7",
doi = "10.18653/v1/2020.wat-1.7",
pages = "80--91",
abstract = "We introduce our TMU system submitted to the Japanese{\textless}-{\textgreater}English Multimodal Task (constrained) for WAT 2020 (Nakazawa et al., 2020). This task aims to improve translation performance with the help of another modality (images) associated with the input sentences. In a multimodal translation task, the dataset is, by its nature, a low-resource one. Our method used herein augments the data by generating noisy translations and adding noise to existing training images. Subsequently, we pretrain a translation model on the augmented noisy data, and then fine-tune it on the clean data. We also examine the probabilistic dropping of either the textual or visual context vector in the decoder. This aims to regularize the network to make use of both features while training. The experimental results indicate that translation performance can be improved using our method of textual data augmentation with noising on the target side and probabilistic dropping of either context vector.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tamura-etal-2020-tmu">
<titleInfo>
<title>TMU Japanese-English Multimodal Machine Translation System for WAT 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroto</namePart>
<namePart type="family">Tamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tosho</namePart>
<namePart type="family">Hirasawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masahiro</namePart>
<namePart type="family">Kaneko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Asian Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Win</namePart>
<namePart type="given">Pa</namePart>
<namePart type="family">Pa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidaya</namePart>
<namePart type="family">Mino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroshi</namePart>
<namePart type="family">Manabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce our TMU system submitted to the Japanese\textless-\textgreaterEnglish Multimodal Task (constrained) for WAT 2020 (Nakazawa et al., 2020). This task aims to improve translation performance with the help of another modality (images) associated with the input sentences. In a multimodal translation task, the dataset is, by its nature, a low-resource one. Our method used herein augments the data by generating noisy translations and adding noise to existing training images. Subsequently, we pretrain a translation model on the augmented noisy data, and then fine-tune it on the clean data. We also examine the probabilistic dropping of either the textual or visual context vector in the decoder. This aims to regularize the network to make use of both features while training. The experimental results indicate that translation performance can be improved using our method of textual data augmentation with noising on the target side and probabilistic dropping of either context vector.</abstract>
<identifier type="citekey">tamura-etal-2020-tmu</identifier>
<identifier type="doi">10.18653/v1/2020.wat-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.wat-1.7</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>80</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TMU Japanese-English Multimodal Machine Translation System for WAT 2020
%A Tamura, Hiroto
%A Hirasawa, Tosho
%A Kaneko, Masahiro
%A Komachi, Mamoru
%Y Nakazawa, Toshiaki
%Y Nakayama, Hideki
%Y Ding, Chenchen
%Y Dabre, Raj
%Y Kunchukuttan, Anoop
%Y Pa, Win Pa
%Y Bojar, Ondřej
%Y Parida, Shantipriya
%Y Goto, Isao
%Y Mino, Hidaya
%Y Manabe, Hiroshi
%Y Sudoh, Katsuhito
%Y Kurohashi, Sadao
%Y Bhattacharyya, Pushpak
%S Proceedings of the 7th Workshop on Asian Translation
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F tamura-etal-2020-tmu
%X We introduce our TMU system submitted to the Japanese\textless-\textgreaterEnglish Multimodal Task (constrained) for WAT 2020 (Nakazawa et al., 2020). This task aims to improve translation performance with the help of another modality (images) associated with the input sentences. In a multimodal translation task, the dataset is, by its nature, a low-resource one. Our method used herein augments the data by generating noisy translations and adding noise to existing training images. Subsequently, we pretrain a translation model on the augmented noisy data, and then fine-tune it on the clean data. We also examine the probabilistic dropping of either the textual or visual context vector in the decoder. This aims to regularize the network to make use of both features while training. The experimental results indicate that translation performance can be improved using our method of textual data augmentation with noising on the target side and probabilistic dropping of either context vector.
%R 10.18653/v1/2020.wat-1.7
%U https://aclanthology.org/2020.wat-1.7
%U https://doi.org/10.18653/v1/2020.wat-1.7
%P 80-91
Markdown (Informal)
[TMU Japanese-English Multimodal Machine Translation System for WAT 2020](https://aclanthology.org/2020.wat-1.7) (Tamura et al., WAT 2020)
ACL