@inproceedings{bourlon-etal-2016-simultaneous,
title = "Simultaneous Sentence Boundary Detection and Alignment with Pivot-based Machine Translation Generated Lexicons",
author = "Bourlon, Antoine and
Chu, Chenhui and
Nakazawa, Toshiaki and
Kurohashi, Sadao",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1348",
pages = "2192--2198",
abstract = "Sentence alignment is a task that consists in aligning the parallel sentences in a translated article pair. This paper describes a method to perform sentence boundary detection and alignment simultaneously, which significantly improves the alignment accuracy on languages like Chinese with uncertain sentence boundaries. It relies on the definition of hard (certain) and soft (uncertain) punctuation delimiters, the latter being possibly ignored to optimize the alignment result. The alignment method is used in combination with lexicons automatically generated from the input article pairs using pivot-based MT, achieving better coverage of the input words with fewer entries than pre-existing dictionaries. Pivot-based MT makes it possible to build dictionaries for language pairs that have scarce parallel data. The alignment method is implemented in a tool that will be freely available in the near future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bourlon-etal-2016-simultaneous">
<titleInfo>
<title>Simultaneous Sentence Boundary Detection and Alignment with Pivot-based Machine Translation Generated Lexicons</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bourlon</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>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentence alignment is a task that consists in aligning the parallel sentences in a translated article pair. This paper describes a method to perform sentence boundary detection and alignment simultaneously, which significantly improves the alignment accuracy on languages like Chinese with uncertain sentence boundaries. It relies on the definition of hard (certain) and soft (uncertain) punctuation delimiters, the latter being possibly ignored to optimize the alignment result. The alignment method is used in combination with lexicons automatically generated from the input article pairs using pivot-based MT, achieving better coverage of the input words with fewer entries than pre-existing dictionaries. Pivot-based MT makes it possible to build dictionaries for language pairs that have scarce parallel data. The alignment method is implemented in a tool that will be freely available in the near future.</abstract>
<identifier type="citekey">bourlon-etal-2016-simultaneous</identifier>
<location>
<url>https://aclanthology.org/L16-1348</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2192</start>
<end>2198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simultaneous Sentence Boundary Detection and Alignment with Pivot-based Machine Translation Generated Lexicons
%A Bourlon, Antoine
%A Chu, Chenhui
%A Nakazawa, Toshiaki
%A Kurohashi, Sadao
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F bourlon-etal-2016-simultaneous
%X Sentence alignment is a task that consists in aligning the parallel sentences in a translated article pair. This paper describes a method to perform sentence boundary detection and alignment simultaneously, which significantly improves the alignment accuracy on languages like Chinese with uncertain sentence boundaries. It relies on the definition of hard (certain) and soft (uncertain) punctuation delimiters, the latter being possibly ignored to optimize the alignment result. The alignment method is used in combination with lexicons automatically generated from the input article pairs using pivot-based MT, achieving better coverage of the input words with fewer entries than pre-existing dictionaries. Pivot-based MT makes it possible to build dictionaries for language pairs that have scarce parallel data. The alignment method is implemented in a tool that will be freely available in the near future.
%U https://aclanthology.org/L16-1348
%P 2192-2198
Markdown (Informal)
[Simultaneous Sentence Boundary Detection and Alignment with Pivot-based Machine Translation Generated Lexicons](https://aclanthology.org/L16-1348) (Bourlon et al., LREC 2016)
ACL