@inproceedings{quispesaravia-etal-2016-coh,
title = "{C}oh-{M}etrix-{E}sp: A Complexity Analysis Tool for Documents Written in {S}panish",
author = "Quispesaravia, Andre and
Perez, Walter and
Sobrevilla Cabezudo, Marco and
Alva-Manchego, Fernando",
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/L16-1745",
pages = "4694--4698",
abstract = "Text Complexity Analysis is an useful task in Education. For example, it can help teachers select appropriate texts for their students according to their educational level. This task requires the analysis of several text features that people do mostly manually (e.g. syntactic complexity, words variety, etc.). In this paper, we present a tool useful for Complexity Analysis, called Coh-Metrix-Esp. This is the Spanish version of Coh-Metrix and is able to calculate 45 readability indices. We analyse how these indices behave in a corpus of {``}simple{''} and {``}complex{''} documents, and also use them as features in a complexity binary classifier for texts in Spanish. After some experiments with machine learning algorithms, we got 0.9 F-measure for a corpus that contains tales for kids and adults and 0.82 F-measure for a corpus with texts written for students of Spanish as a foreign language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="quispesaravia-etal-2016-coh">
<titleInfo>
<title>Coh-Metrix-Esp: A Complexity Analysis Tool for Documents Written in Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Quispesaravia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Perez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Sobrevilla Cabezudo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</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>Text Complexity Analysis is an useful task in Education. For example, it can help teachers select appropriate texts for their students according to their educational level. This task requires the analysis of several text features that people do mostly manually (e.g. syntactic complexity, words variety, etc.). In this paper, we present a tool useful for Complexity Analysis, called Coh-Metrix-Esp. This is the Spanish version of Coh-Metrix and is able to calculate 45 readability indices. We analyse how these indices behave in a corpus of “simple” and “complex” documents, and also use them as features in a complexity binary classifier for texts in Spanish. After some experiments with machine learning algorithms, we got 0.9 F-measure for a corpus that contains tales for kids and adults and 0.82 F-measure for a corpus with texts written for students of Spanish as a foreign language.</abstract>
<identifier type="citekey">quispesaravia-etal-2016-coh</identifier>
<location>
<url>https://aclanthology.org/L16-1745</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4694</start>
<end>4698</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coh-Metrix-Esp: A Complexity Analysis Tool for Documents Written in Spanish
%A Quispesaravia, Andre
%A Perez, Walter
%A Sobrevilla Cabezudo, Marco
%A Alva-Manchego, Fernando
%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 quispesaravia-etal-2016-coh
%X Text Complexity Analysis is an useful task in Education. For example, it can help teachers select appropriate texts for their students according to their educational level. This task requires the analysis of several text features that people do mostly manually (e.g. syntactic complexity, words variety, etc.). In this paper, we present a tool useful for Complexity Analysis, called Coh-Metrix-Esp. This is the Spanish version of Coh-Metrix and is able to calculate 45 readability indices. We analyse how these indices behave in a corpus of “simple” and “complex” documents, and also use them as features in a complexity binary classifier for texts in Spanish. After some experiments with machine learning algorithms, we got 0.9 F-measure for a corpus that contains tales for kids and adults and 0.82 F-measure for a corpus with texts written for students of Spanish as a foreign language.
%U https://aclanthology.org/L16-1745
%P 4694-4698
Markdown (Informal)
[Coh-Metrix-Esp: A Complexity Analysis Tool for Documents Written in Spanish](https://aclanthology.org/L16-1745) (Quispesaravia et al., LREC 2016)
ACL