@inproceedings{zhu-etal-2023-leveraging,
title = "Leveraging Highly Accurate Word Alignment for Low Resource Translation by Pretrained Multilingual Model",
author = "Zhu, Jingyi and
Kondo, Minato and
Tamura, Takuya and
Utsuro, Takehito and
Nagata, Masaaki",
editor = "Utiyama, Masao and
Wang, Rui",
booktitle = "Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track",
month = sep,
year = "2023",
address = "Macau SAR, China",
publisher = "Asia-Pacific Association for Machine Translation",
url = "https://aclanthology.org/2023.mtsummit-research.28",
pages = "336--347",
abstract = "Recently, there has been a growing interest in pretraining models in the field of natural language processing. As opposed to training models from scratch, pretrained models have been shown to produce superior results in low-resource translation tasks. In this paper, we introduced the use of pretrained seq2seq models for preordering and translation tasks. We utilized manual word alignment data and mBERT-based generated word alignment data for training preordering and compared the effectiveness of various types of mT5 and mBART models for preordering. For the translation task, we chose mBART as our baseline model and evaluated several input manners. Our approach was evaluated on the Asian Language Treebank dataset, consisting of 20,000 parallel data in Japanese, English and Hindi, where Japanese is either on the source or target side. We also used in-house 3,000 parallel data in Chinese and Japanese. The results indicated that mT5-large trained with manual word alignment achieved a preordering performance exceeding 0.9 RIBES score on Ja-En and Ja-Zh pairs. Moreover, our proposed approach significantly outperformed the baseline model in most translation directions of Ja-En, Ja-Zh, and Ja-Hi pairs in at least one of BLEU/COMET scores.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2023-leveraging">
<titleInfo>
<title>Leveraging Highly Accurate Word Alignment for Low Resource Translation by Pretrained Multilingual Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingyi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minato</namePart>
<namePart type="family">Kondo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takuya</namePart>
<namePart type="family">Tamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asia-Pacific Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Macau SAR, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, there has been a growing interest in pretraining models in the field of natural language processing. As opposed to training models from scratch, pretrained models have been shown to produce superior results in low-resource translation tasks. In this paper, we introduced the use of pretrained seq2seq models for preordering and translation tasks. We utilized manual word alignment data and mBERT-based generated word alignment data for training preordering and compared the effectiveness of various types of mT5 and mBART models for preordering. For the translation task, we chose mBART as our baseline model and evaluated several input manners. Our approach was evaluated on the Asian Language Treebank dataset, consisting of 20,000 parallel data in Japanese, English and Hindi, where Japanese is either on the source or target side. We also used in-house 3,000 parallel data in Chinese and Japanese. The results indicated that mT5-large trained with manual word alignment achieved a preordering performance exceeding 0.9 RIBES score on Ja-En and Ja-Zh pairs. Moreover, our proposed approach significantly outperformed the baseline model in most translation directions of Ja-En, Ja-Zh, and Ja-Hi pairs in at least one of BLEU/COMET scores.</abstract>
<identifier type="citekey">zhu-etal-2023-leveraging</identifier>
<location>
<url>https://aclanthology.org/2023.mtsummit-research.28</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>336</start>
<end>347</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Highly Accurate Word Alignment for Low Resource Translation by Pretrained Multilingual Model
%A Zhu, Jingyi
%A Kondo, Minato
%A Tamura, Takuya
%A Utsuro, Takehito
%A Nagata, Masaaki
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F zhu-etal-2023-leveraging
%X Recently, there has been a growing interest in pretraining models in the field of natural language processing. As opposed to training models from scratch, pretrained models have been shown to produce superior results in low-resource translation tasks. In this paper, we introduced the use of pretrained seq2seq models for preordering and translation tasks. We utilized manual word alignment data and mBERT-based generated word alignment data for training preordering and compared the effectiveness of various types of mT5 and mBART models for preordering. For the translation task, we chose mBART as our baseline model and evaluated several input manners. Our approach was evaluated on the Asian Language Treebank dataset, consisting of 20,000 parallel data in Japanese, English and Hindi, where Japanese is either on the source or target side. We also used in-house 3,000 parallel data in Chinese and Japanese. The results indicated that mT5-large trained with manual word alignment achieved a preordering performance exceeding 0.9 RIBES score on Ja-En and Ja-Zh pairs. Moreover, our proposed approach significantly outperformed the baseline model in most translation directions of Ja-En, Ja-Zh, and Ja-Hi pairs in at least one of BLEU/COMET scores.
%U https://aclanthology.org/2023.mtsummit-research.28
%P 336-347
Markdown (Informal)
[Leveraging Highly Accurate Word Alignment for Low Resource Translation by Pretrained Multilingual Model](https://aclanthology.org/2023.mtsummit-research.28) (Zhu et al., MTSummit 2023)
ACL