@inproceedings{rodriguez-ferreira-etal-2016-improving,
title = "Improving Information Extraction from {W}ikipedia Texts using Basic {E}nglish",
author = "Rodr{\'\i}guez-Ferreira, Teresa and
Rabad{\'a}n, Adri{\'a}n and
Herv{\'a}s, Raquel and
D{\'\i}az, Alberto",
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/L16-1062",
pages = "395--400",
abstract = "The aim of this paper is to study the effect that the use of Basic English versus common English has on information extraction from online resources. The amount of online information available to the public grows exponentially, and is potentially an excellent resource for information extraction. The problem is that this information often comes in an unstructured format, such as plain text. In order to retrieve knowledge from this type of text, it must first be analysed to find the relevant details, and the nature of the language used can greatly impact the quality of the extracted information. In this paper, we compare triplets that represent definitions or properties of concepts obtained from three online collaborative resources (English Wikipedia, Simple English Wikipedia and Simple English Wiktionary) and study the differences in the results when Basic English is used instead of common English. The results show that resources written in Basic English produce less quantity of triplets, but with higher quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-ferreira-etal-2016-improving">
<titleInfo>
<title>Improving Information Extraction from Wikipedia Texts using Basic English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Rodríguez-Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrián</namePart>
<namePart type="family">Rabadán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Hervás</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Díaz</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>The aim of this paper is to study the effect that the use of Basic English versus common English has on information extraction from online resources. The amount of online information available to the public grows exponentially, and is potentially an excellent resource for information extraction. The problem is that this information often comes in an unstructured format, such as plain text. In order to retrieve knowledge from this type of text, it must first be analysed to find the relevant details, and the nature of the language used can greatly impact the quality of the extracted information. In this paper, we compare triplets that represent definitions or properties of concepts obtained from three online collaborative resources (English Wikipedia, Simple English Wikipedia and Simple English Wiktionary) and study the differences in the results when Basic English is used instead of common English. The results show that resources written in Basic English produce less quantity of triplets, but with higher quality.</abstract>
<identifier type="citekey">rodriguez-ferreira-etal-2016-improving</identifier>
<location>
<url>https://aclanthology.org/L16-1062</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>395</start>
<end>400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Information Extraction from Wikipedia Texts using Basic English
%A Rodríguez-Ferreira, Teresa
%A Rabadán, Adrián
%A Hervás, Raquel
%A Díaz, Alberto
%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 rodriguez-ferreira-etal-2016-improving
%X The aim of this paper is to study the effect that the use of Basic English versus common English has on information extraction from online resources. The amount of online information available to the public grows exponentially, and is potentially an excellent resource for information extraction. The problem is that this information often comes in an unstructured format, such as plain text. In order to retrieve knowledge from this type of text, it must first be analysed to find the relevant details, and the nature of the language used can greatly impact the quality of the extracted information. In this paper, we compare triplets that represent definitions or properties of concepts obtained from three online collaborative resources (English Wikipedia, Simple English Wikipedia and Simple English Wiktionary) and study the differences in the results when Basic English is used instead of common English. The results show that resources written in Basic English produce less quantity of triplets, but with higher quality.
%U https://aclanthology.org/L16-1062
%P 395-400
Markdown (Informal)
[Improving Information Extraction from Wikipedia Texts using Basic English](https://aclanthology.org/L16-1062) (Rodríguez-Ferreira et al., LREC 2016)
ACL