@inproceedings{parida-bojar-2018-translating,
title = "Translating Short Segments with {NMT}: A Case Study in {E}nglish-to-{H}indi",
author = "Parida, Shantipriya and
Bojar, Ond{\v{r}}ej",
editor = "P{\'e}rez-Ortiz, Juan Antonio and
S{\'a}nchez-Mart{\'\i}nez, Felipe and
Espl{\`a}-Gomis, Miquel and
Popovi{\'c}, Maja and
Rico, Celia and
Martins, Andr{\'e} and
Van den Bogaert, Joachim and
Forcada, Mikel L.",
booktitle = "Proceedings of the 21st Annual Conference of the European Association for Machine Translation",
month = may,
year = "2018",
address = "Alicante, Spain",
url = "https://aclanthology.org/2018.eamt-main.23",
pages = "249--258",
abstract = "This paper presents a case study in translating short image captions of the Visual Genome dataset from English into Hindi using out-of-domain data sets of varying size. We experiment with three NMT models: the shallow and deep sequence-tosequence and the Transformer model as implemented in Marian toolkit. Phrase-based Moses serves as the baseline. The results indicate that the Transformer model outperforms others in the large data setting in a number of automatic metrics and manual evaluation, and it also produces the fewest truncated sentences. Transformer training is however very sensitive to the hyperparameters, so it requires more experimenting. The deep sequence-to-sequence model produced more flawless outputs in the small data setting and it was generally more stable, at the cost of more training iterations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parida-bojar-2018-translating">
<titleInfo>
<title>Translating Short Segments with NMT: A Case Study in English-to-Hindi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celia</namePart>
<namePart type="family">Rico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Alicante, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a case study in translating short image captions of the Visual Genome dataset from English into Hindi using out-of-domain data sets of varying size. We experiment with three NMT models: the shallow and deep sequence-tosequence and the Transformer model as implemented in Marian toolkit. Phrase-based Moses serves as the baseline. The results indicate that the Transformer model outperforms others in the large data setting in a number of automatic metrics and manual evaluation, and it also produces the fewest truncated sentences. Transformer training is however very sensitive to the hyperparameters, so it requires more experimenting. The deep sequence-to-sequence model produced more flawless outputs in the small data setting and it was generally more stable, at the cost of more training iterations.</abstract>
<identifier type="citekey">parida-bojar-2018-translating</identifier>
<location>
<url>https://aclanthology.org/2018.eamt-main.23</url>
</location>
<part>
<date>2018-05</date>
<extent unit="page">
<start>249</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translating Short Segments with NMT: A Case Study in English-to-Hindi
%A Parida, Shantipriya
%A Bojar, Ondřej
%Y Pérez-Ortiz, Juan Antonio
%Y Sánchez-Martínez, Felipe
%Y Esplà-Gomis, Miquel
%Y Popović, Maja
%Y Rico, Celia
%Y Martins, André
%Y Van den Bogaert, Joachim
%Y Forcada, Mikel L.
%S Proceedings of the 21st Annual Conference of the European Association for Machine Translation
%D 2018
%8 May
%C Alicante, Spain
%F parida-bojar-2018-translating
%X This paper presents a case study in translating short image captions of the Visual Genome dataset from English into Hindi using out-of-domain data sets of varying size. We experiment with three NMT models: the shallow and deep sequence-tosequence and the Transformer model as implemented in Marian toolkit. Phrase-based Moses serves as the baseline. The results indicate that the Transformer model outperforms others in the large data setting in a number of automatic metrics and manual evaluation, and it also produces the fewest truncated sentences. Transformer training is however very sensitive to the hyperparameters, so it requires more experimenting. The deep sequence-to-sequence model produced more flawless outputs in the small data setting and it was generally more stable, at the cost of more training iterations.
%U https://aclanthology.org/2018.eamt-main.23
%P 249-258
Markdown (Informal)
[Translating Short Segments with NMT: A Case Study in English-to-Hindi](https://aclanthology.org/2018.eamt-main.23) (Parida & Bojar, EAMT 2018)
ACL