@inproceedings{liu-etal-2019-incorporating-word,
title = "Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring",
author = "Liu, Zihan and
Xu, Yan and
Winata, Genta Indra and
Fung, Pascale",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5327",
doi = "10.18653/v1/W19-5327",
pages = "275--282",
abstract = "This paper describes CAiRE{'}s submission to the unsupervised machine translation track of the WMT{'}19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consistency of translations, a rescoring mechanism is proposed that reuses the pre-trained language model to select the translation candidates generated through beam search. Moreover, a series of pre-processing and post-processing approaches are applied to improve the quality of final translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2019-incorporating-word">
<titleInfo>
<title>Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes CAiRE’s submission to the unsupervised machine translation track of the WMT’19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consistency of translations, a rescoring mechanism is proposed that reuses the pre-trained language model to select the translation candidates generated through beam search. Moreover, a series of pre-processing and post-processing approaches are applied to improve the quality of final translations.</abstract>
<identifier type="citekey">liu-etal-2019-incorporating-word</identifier>
<identifier type="doi">10.18653/v1/W19-5327</identifier>
<location>
<url>https://aclanthology.org/W19-5327</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>275</start>
<end>282</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
%A Liu, Zihan
%A Xu, Yan
%A Winata, Genta Indra
%A Fung, Pascale
%S Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F liu-etal-2019-incorporating-word
%X This paper describes CAiRE’s submission to the unsupervised machine translation track of the WMT’19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consistency of translations, a rescoring mechanism is proposed that reuses the pre-trained language model to select the translation candidates generated through beam search. Moreover, a series of pre-processing and post-processing approaches are applied to improve the quality of final translations.
%R 10.18653/v1/W19-5327
%U https://aclanthology.org/W19-5327
%U https://doi.org/10.18653/v1/W19-5327
%P 275-282
Markdown (Informal)
[Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring](https://aclanthology.org/W19-5327) (Liu et al., 2019)
ACL