@inproceedings{zhu-xiong-2023-tjunlp,
title = "{TJUNLP}:System Description for the {WMT}23 Literary Task in {C}hinese to {E}nglish Translation Direction",
author = "Zhu, Shaolin and
Xiong, Deyi",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.33/",
doi = "10.18653/v1/2023.wmt-1.33",
pages = "307--311",
abstract = "This paper introduces the overall situation of the Natural Language Processing Laboratory of Tianjin University participating in the WMT23 machine translation evaluation task from Chinese to English. For this evaluation, the base model used is a Transformer based on a Mixture of Experts (MOE) model. During the model`s construction and training, a basic dense model based on Transformer is first trained on the training set. Then, this model is used to initialize the MOE-based translation model, which is further trained on the training corpus. Since the training dataset provided for this translation task is relatively small, to better utilize sparse models to enhance translation, we employed a data augmentation technique for alignment. Experimental results show that this method can effectively improve neural machine translation performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-xiong-2023-tjunlp">
<titleInfo>
<title>TJUNLP:System Description for the WMT23 Literary Task in Chinese to English Translation Direction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaolin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</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>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</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>This paper introduces the overall situation of the Natural Language Processing Laboratory of Tianjin University participating in the WMT23 machine translation evaluation task from Chinese to English. For this evaluation, the base model used is a Transformer based on a Mixture of Experts (MOE) model. During the model‘s construction and training, a basic dense model based on Transformer is first trained on the training set. Then, this model is used to initialize the MOE-based translation model, which is further trained on the training corpus. Since the training dataset provided for this translation task is relatively small, to better utilize sparse models to enhance translation, we employed a data augmentation technique for alignment. Experimental results show that this method can effectively improve neural machine translation performance.</abstract>
<identifier type="citekey">zhu-xiong-2023-tjunlp</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.33</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.33/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>307</start>
<end>311</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TJUNLP:System Description for the WMT23 Literary Task in Chinese to English Translation Direction
%A Zhu, Shaolin
%A Xiong, Deyi
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhu-xiong-2023-tjunlp
%X This paper introduces the overall situation of the Natural Language Processing Laboratory of Tianjin University participating in the WMT23 machine translation evaluation task from Chinese to English. For this evaluation, the base model used is a Transformer based on a Mixture of Experts (MOE) model. During the model‘s construction and training, a basic dense model based on Transformer is first trained on the training set. Then, this model is used to initialize the MOE-based translation model, which is further trained on the training corpus. Since the training dataset provided for this translation task is relatively small, to better utilize sparse models to enhance translation, we employed a data augmentation technique for alignment. Experimental results show that this method can effectively improve neural machine translation performance.
%R 10.18653/v1/2023.wmt-1.33
%U https://aclanthology.org/2023.wmt-1.33/
%U https://doi.org/10.18653/v1/2023.wmt-1.33
%P 307-311
Markdown (Informal)
[TJUNLP:System Description for the WMT23 Literary Task in Chinese to English Translation Direction](https://aclanthology.org/2023.wmt-1.33/) (Zhu & Xiong, WMT 2023)
ACL