@inproceedings{vandeghinste-etal-2018-comparison,
title = "A Comparison of Different Punctuation Prediction Approaches in a Translation Context",
author = "Vandeghinste, Vincent and
Verwimp, Lyan and
Pelemans, Joris and
Wambacq, Patrick",
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.27",
pages = "289--298",
abstract = "We test a series of techniques to predict punctuation and its effect on machine translation (MT) quality. Several techniques for punctuation prediction are compared: language modeling techniques, such as n-grams and long shortterm memories (LSTM), sequence labeling LSTMs (unidirectional and bidirectional), and monolingual phrase-based, hierarchical and neural MT. For actual translation, phrase-based, hierarchical and neural MT are investigated. We observe that for punctuation prediction, phrase-based statistical MT and neural MT reach similar results, and are best used as a preprocessing step which is followed by neural MT to perform the actual translation. Implicit punctuation insertion by a dedicated neural MT system, trained on unpunctuated source and punctuated target, yields similar results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vandeghinste-etal-2018-comparison">
<titleInfo>
<title>A Comparison of Different Punctuation Prediction Approaches in a Translation Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Vandeghinste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyan</namePart>
<namePart type="family">Verwimp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Pelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Wambacq</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>We test a series of techniques to predict punctuation and its effect on machine translation (MT) quality. Several techniques for punctuation prediction are compared: language modeling techniques, such as n-grams and long shortterm memories (LSTM), sequence labeling LSTMs (unidirectional and bidirectional), and monolingual phrase-based, hierarchical and neural MT. For actual translation, phrase-based, hierarchical and neural MT are investigated. We observe that for punctuation prediction, phrase-based statistical MT and neural MT reach similar results, and are best used as a preprocessing step which is followed by neural MT to perform the actual translation. Implicit punctuation insertion by a dedicated neural MT system, trained on unpunctuated source and punctuated target, yields similar results.</abstract>
<identifier type="citekey">vandeghinste-etal-2018-comparison</identifier>
<location>
<url>https://aclanthology.org/2018.eamt-main.27</url>
</location>
<part>
<date>2018-05</date>
<extent unit="page">
<start>289</start>
<end>298</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparison of Different Punctuation Prediction Approaches in a Translation Context
%A Vandeghinste, Vincent
%A Verwimp, Lyan
%A Pelemans, Joris
%A Wambacq, Patrick
%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 vandeghinste-etal-2018-comparison
%X We test a series of techniques to predict punctuation and its effect on machine translation (MT) quality. Several techniques for punctuation prediction are compared: language modeling techniques, such as n-grams and long shortterm memories (LSTM), sequence labeling LSTMs (unidirectional and bidirectional), and monolingual phrase-based, hierarchical and neural MT. For actual translation, phrase-based, hierarchical and neural MT are investigated. We observe that for punctuation prediction, phrase-based statistical MT and neural MT reach similar results, and are best used as a preprocessing step which is followed by neural MT to perform the actual translation. Implicit punctuation insertion by a dedicated neural MT system, trained on unpunctuated source and punctuated target, yields similar results.
%U https://aclanthology.org/2018.eamt-main.27
%P 289-298
Markdown (Informal)
[A Comparison of Different Punctuation Prediction Approaches in a Translation Context](https://aclanthology.org/2018.eamt-main.27) (Vandeghinste et al., EAMT 2018)
ACL