@inproceedings{cardon-grabar-2018-identification,
title = "Identification of Parallel Sentences in Comparable Monolingual Corpora from Different Registers",
author = "Cardon, R{\'e}mi and
Grabar, Natalia",
editor = "Lavelli, Alberto and
Minard, Anne-Lyse and
Rinaldi, Fabio",
booktitle = "Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5610",
doi = "10.18653/v1/W18-5610",
pages = "83--93",
abstract = "Parallel aligned sentences provide useful information for different NLP applications. Yet, this kind of data is seldom available, especially for languages other than English. We propose to exploit comparable corpora in French which are distinguished by their registers (specialized and simplified versions) to detect and align parallel sentences. These corpora are related to the biomedical area. Our purpose is to state whether a given pair of specialized and simplified sentences is to be aligned or not. Manually created reference data show 0.76 inter-annotator agreement. We exploit a set of features and several automatic classifiers. The automatic alignment reaches up to 0.93 Precision, Recall and F-measure. In order to better evaluate the method, it is applied to data in English from the \textit{SemEval} STS competitions. The same features and models are applied in monolingual and cross-lingual contexts, in which they show up to 0.90 and 0.73 F-measure, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cardon-grabar-2018-identification">
<titleInfo>
<title>Identification of Parallel Sentences in Comparable Monolingual Corpora from Different Registers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Grabar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel aligned sentences provide useful information for different NLP applications. Yet, this kind of data is seldom available, especially for languages other than English. We propose to exploit comparable corpora in French which are distinguished by their registers (specialized and simplified versions) to detect and align parallel sentences. These corpora are related to the biomedical area. Our purpose is to state whether a given pair of specialized and simplified sentences is to be aligned or not. Manually created reference data show 0.76 inter-annotator agreement. We exploit a set of features and several automatic classifiers. The automatic alignment reaches up to 0.93 Precision, Recall and F-measure. In order to better evaluate the method, it is applied to data in English from the SemEval STS competitions. The same features and models are applied in monolingual and cross-lingual contexts, in which they show up to 0.90 and 0.73 F-measure, respectively.</abstract>
<identifier type="citekey">cardon-grabar-2018-identification</identifier>
<identifier type="doi">10.18653/v1/W18-5610</identifier>
<location>
<url>https://aclanthology.org/W18-5610</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>83</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identification of Parallel Sentences in Comparable Monolingual Corpora from Different Registers
%A Cardon, Rémi
%A Grabar, Natalia
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Rinaldi, Fabio
%S Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F cardon-grabar-2018-identification
%X Parallel aligned sentences provide useful information for different NLP applications. Yet, this kind of data is seldom available, especially for languages other than English. We propose to exploit comparable corpora in French which are distinguished by their registers (specialized and simplified versions) to detect and align parallel sentences. These corpora are related to the biomedical area. Our purpose is to state whether a given pair of specialized and simplified sentences is to be aligned or not. Manually created reference data show 0.76 inter-annotator agreement. We exploit a set of features and several automatic classifiers. The automatic alignment reaches up to 0.93 Precision, Recall and F-measure. In order to better evaluate the method, it is applied to data in English from the SemEval STS competitions. The same features and models are applied in monolingual and cross-lingual contexts, in which they show up to 0.90 and 0.73 F-measure, respectively.
%R 10.18653/v1/W18-5610
%U https://aclanthology.org/W18-5610
%U https://doi.org/10.18653/v1/W18-5610
%P 83-93
Markdown (Informal)
[Identification of Parallel Sentences in Comparable Monolingual Corpora from Different Registers](https://aclanthology.org/W18-5610) (Cardon & Grabar, Louhi 2018)
ACL