@inproceedings{le-etal-2021-illinois,
title = "{I}llinois {J}apanese $\leftrightarrow$ {E}nglish {N}ews {T}ranslation for {WMT} 2021",
author = "Le, Giang and
Mori, Shinka and
Schwartz, Lane",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.11",
pages = "144--153",
abstract = "This system paper describes an end-to-end NMT pipeline for the Japanese $\leftrightarrow$ English news translation task as submitted to WMT 2021, where we explore the efficacy of techniques such as tokenizing with language-independent and language-dependent tokenizers, normalizing by orthographic conversion, creating a politeness-and-formality-aware model by implementing a tagger, back-translation, model ensembling, and n-best reranking. We use parallel corpora provided by WMT 2021 organizers for training, and development and test data from WMT 2020 for evaluation of different experiment models. The preprocessed corpora are trained with a Transformer neural network model. We found that combining various techniques described herein, such as language-independent BPE tokenization, incorporating politeness and formality tags, model ensembling, n-best reranking, and back-translation produced the best translation models relative to other experiment systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-etal-2021-illinois">
<titleInfo>
<title>Illinois Japanese $\leftrightarrow$ English News Translation for WMT 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giang</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinka</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This system paper describes an end-to-end NMT pipeline for the Japanese $\leftrightarrow$ English news translation task as submitted to WMT 2021, where we explore the efficacy of techniques such as tokenizing with language-independent and language-dependent tokenizers, normalizing by orthographic conversion, creating a politeness-and-formality-aware model by implementing a tagger, back-translation, model ensembling, and n-best reranking. We use parallel corpora provided by WMT 2021 organizers for training, and development and test data from WMT 2020 for evaluation of different experiment models. The preprocessed corpora are trained with a Transformer neural network model. We found that combining various techniques described herein, such as language-independent BPE tokenization, incorporating politeness and formality tags, model ensembling, n-best reranking, and back-translation produced the best translation models relative to other experiment systems.</abstract>
<identifier type="citekey">le-etal-2021-illinois</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.11</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>144</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Illinois Japanese $\leftrightarrow$ English News Translation for WMT 2021
%A Le, Giang
%A Mori, Shinka
%A Schwartz, Lane
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F le-etal-2021-illinois
%X This system paper describes an end-to-end NMT pipeline for the Japanese $\leftrightarrow$ English news translation task as submitted to WMT 2021, where we explore the efficacy of techniques such as tokenizing with language-independent and language-dependent tokenizers, normalizing by orthographic conversion, creating a politeness-and-formality-aware model by implementing a tagger, back-translation, model ensembling, and n-best reranking. We use parallel corpora provided by WMT 2021 organizers for training, and development and test data from WMT 2020 for evaluation of different experiment models. The preprocessed corpora are trained with a Transformer neural network model. We found that combining various techniques described herein, such as language-independent BPE tokenization, incorporating politeness and formality tags, model ensembling, n-best reranking, and back-translation produced the best translation models relative to other experiment systems.
%U https://aclanthology.org/2021.wmt-1.11
%P 144-153
Markdown (Informal)
[Illinois Japanese ↔ English News Translation for WMT 2021](https://aclanthology.org/2021.wmt-1.11) (Le et al., WMT 2021)
ACL