@inproceedings{poncelas-way-2019-selecting,
title = "Selecting Artificially-Generated Sentences for Fine-Tuning Neural Machine Translation",
author = "Poncelas, Alberto and
Way, Andy",
editor = "van Deemter, Kees and
Lin, Chenghua and
Takamura, Hiroya",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8629",
doi = "10.18653/v1/W19-8629",
pages = "219--228",
abstract = "Neural Machine Translation (NMT) models tend to achieve the best performances when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pair can boost the performance. Nonetheless, the performance can also be improved with a small number of sentences if they are in the same domain as the test set. Accordingly, we want to explore the use of artificially-generated sentence along with data-selection algorithms to improve NMT models trained solely with authentic data. In this work, we show how artificially-generated sentences can be more beneficial than authentic pairs and what are their advantages when used in combination with data-selection algorithms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poncelas-way-2019-selecting">
<titleInfo>
<title>Selecting Artificially-Generated Sentences for Fine-Tuning Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Poncelas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-oct–nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">van Deemter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) models tend to achieve the best performances when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pair can boost the performance. Nonetheless, the performance can also be improved with a small number of sentences if they are in the same domain as the test set. Accordingly, we want to explore the use of artificially-generated sentence along with data-selection algorithms to improve NMT models trained solely with authentic data. In this work, we show how artificially-generated sentences can be more beneficial than authentic pairs and what are their advantages when used in combination with data-selection algorithms.</abstract>
<identifier type="citekey">poncelas-way-2019-selecting</identifier>
<identifier type="doi">10.18653/v1/W19-8629</identifier>
<location>
<url>https://aclanthology.org/W19-8629</url>
</location>
<part>
<date>2019-oct–nov</date>
<extent unit="page">
<start>219</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Selecting Artificially-Generated Sentences for Fine-Tuning Neural Machine Translation
%A Poncelas, Alberto
%A Way, Andy
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F poncelas-way-2019-selecting
%X Neural Machine Translation (NMT) models tend to achieve the best performances when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pair can boost the performance. Nonetheless, the performance can also be improved with a small number of sentences if they are in the same domain as the test set. Accordingly, we want to explore the use of artificially-generated sentence along with data-selection algorithms to improve NMT models trained solely with authentic data. In this work, we show how artificially-generated sentences can be more beneficial than authentic pairs and what are their advantages when used in combination with data-selection algorithms.
%R 10.18653/v1/W19-8629
%U https://aclanthology.org/W19-8629
%U https://doi.org/10.18653/v1/W19-8629
%P 219-228
Markdown (Informal)
[Selecting Artificially-Generated Sentences for Fine-Tuning Neural Machine Translation](https://aclanthology.org/W19-8629) (Poncelas & Way, INLG 2019)
ACL