@inproceedings{dabre-etal-2019-exploiting,
title = "Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation",
author = "Dabre, Raj and
Fujita, Atsushi and
Chu, Chenhui",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1146",
doi = "10.18653/v1/D19-1146",
pages = "1410--1416",
abstract = "This paper highlights the impressive utility of multi-parallel corpora for transfer learning in a one-to-many low-resource neural machine translation (NMT) setting. We report on a systematic comparison of multistage fine-tuning configurations, consisting of (1) pre-training on an external large (209k{--}440k) parallel corpus for English and a helping target language, (2) mixed pre-training or fine-tuning on a mixture of the external and low-resource (18k) target parallel corpora, and (3) pure fine-tuning on the target parallel corpora. Our experiments confirm that multi-parallel corpora are extremely useful despite their scarcity and content-wise redundancy thus exhibiting the true power of multilingualism. Even when the helping target language is not one of the target languages of our concern, our multistage fine-tuning can give 3{--}9 BLEU score gains over a simple one-to-one model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-etal-2019-exploiting">
<titleInfo>
<title>Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Fujita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper highlights the impressive utility of multi-parallel corpora for transfer learning in a one-to-many low-resource neural machine translation (NMT) setting. We report on a systematic comparison of multistage fine-tuning configurations, consisting of (1) pre-training on an external large (209k–440k) parallel corpus for English and a helping target language, (2) mixed pre-training or fine-tuning on a mixture of the external and low-resource (18k) target parallel corpora, and (3) pure fine-tuning on the target parallel corpora. Our experiments confirm that multi-parallel corpora are extremely useful despite their scarcity and content-wise redundancy thus exhibiting the true power of multilingualism. Even when the helping target language is not one of the target languages of our concern, our multistage fine-tuning can give 3–9 BLEU score gains over a simple one-to-one model.</abstract>
<identifier type="citekey">dabre-etal-2019-exploiting</identifier>
<identifier type="doi">10.18653/v1/D19-1146</identifier>
<location>
<url>https://aclanthology.org/D19-1146</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1410</start>
<end>1416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation
%A Dabre, Raj
%A Fujita, Atsushi
%A Chu, Chenhui
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F dabre-etal-2019-exploiting
%X This paper highlights the impressive utility of multi-parallel corpora for transfer learning in a one-to-many low-resource neural machine translation (NMT) setting. We report on a systematic comparison of multistage fine-tuning configurations, consisting of (1) pre-training on an external large (209k–440k) parallel corpus for English and a helping target language, (2) mixed pre-training or fine-tuning on a mixture of the external and low-resource (18k) target parallel corpora, and (3) pure fine-tuning on the target parallel corpora. Our experiments confirm that multi-parallel corpora are extremely useful despite their scarcity and content-wise redundancy thus exhibiting the true power of multilingualism. Even when the helping target language is not one of the target languages of our concern, our multistage fine-tuning can give 3–9 BLEU score gains over a simple one-to-one model.
%R 10.18653/v1/D19-1146
%U https://aclanthology.org/D19-1146
%U https://doi.org/10.18653/v1/D19-1146
%P 1410-1416
Markdown (Informal)
[Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation](https://aclanthology.org/D19-1146) (Dabre et al., EMNLP-IJCNLP 2019)
ACL