@inproceedings{okinina-etal-2020-ctap,
title = "{CTAP} for {I}talian: Integrating Components for the Analysis of {I}talian into a Multilingual Linguistic Complexity Analysis Tool",
author = "Okinina, Nadezda and
Frey, Jennifer-Carmen and
Weiss, Zarah",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.880",
pages = "7123--7131",
abstract = "Linguistic complexity research being a very actively developing field, an increasing number of text analysis tools are created that use natural language processing techniques for the automatic extraction of quantifiable measures of linguistic complexity. While most tools are designed to analyse only one language, the CTAP open source linguistic complexity measurement tool is capable of processing multiple languages, making cross-lingual comparisons possible. Although it was originally developed for English, the architecture has been ex-tended to support multi-lingual analyses. Here we present the Italian component of CTAP, describe its implementation and compare it to the existing linguistic complexity tools for Italian. Offering general text length statistics and features for lexical, syntactic, and morpho-syntactic complexity (including measures of lexical frequency, lexical diversity, lexical and syntactical variation, part-of-speech density), CTAP is currently the most comprehensive linguistic complexity measurement tool for Italian and the only one allowing the comparison of Italian texts to multiple other languages within one tool.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="okinina-etal-2020-ctap">
<titleInfo>
<title>CTAP for Italian: Integrating Components for the Analysis of Italian into a Multilingual Linguistic Complexity Analysis Tool</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nadezda</namePart>
<namePart type="family">Okinina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer-Carmen</namePart>
<namePart type="family">Frey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zarah</namePart>
<namePart type="family">Weiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Linguistic complexity research being a very actively developing field, an increasing number of text analysis tools are created that use natural language processing techniques for the automatic extraction of quantifiable measures of linguistic complexity. While most tools are designed to analyse only one language, the CTAP open source linguistic complexity measurement tool is capable of processing multiple languages, making cross-lingual comparisons possible. Although it was originally developed for English, the architecture has been ex-tended to support multi-lingual analyses. Here we present the Italian component of CTAP, describe its implementation and compare it to the existing linguistic complexity tools for Italian. Offering general text length statistics and features for lexical, syntactic, and morpho-syntactic complexity (including measures of lexical frequency, lexical diversity, lexical and syntactical variation, part-of-speech density), CTAP is currently the most comprehensive linguistic complexity measurement tool for Italian and the only one allowing the comparison of Italian texts to multiple other languages within one tool.</abstract>
<identifier type="citekey">okinina-etal-2020-ctap</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.880</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7123</start>
<end>7131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CTAP for Italian: Integrating Components for the Analysis of Italian into a Multilingual Linguistic Complexity Analysis Tool
%A Okinina, Nadezda
%A Frey, Jennifer-Carmen
%A Weiss, Zarah
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F okinina-etal-2020-ctap
%X Linguistic complexity research being a very actively developing field, an increasing number of text analysis tools are created that use natural language processing techniques for the automatic extraction of quantifiable measures of linguistic complexity. While most tools are designed to analyse only one language, the CTAP open source linguistic complexity measurement tool is capable of processing multiple languages, making cross-lingual comparisons possible. Although it was originally developed for English, the architecture has been ex-tended to support multi-lingual analyses. Here we present the Italian component of CTAP, describe its implementation and compare it to the existing linguistic complexity tools for Italian. Offering general text length statistics and features for lexical, syntactic, and morpho-syntactic complexity (including measures of lexical frequency, lexical diversity, lexical and syntactical variation, part-of-speech density), CTAP is currently the most comprehensive linguistic complexity measurement tool for Italian and the only one allowing the comparison of Italian texts to multiple other languages within one tool.
%U https://aclanthology.org/2020.lrec-1.880
%P 7123-7131
Markdown (Informal)
[CTAP for Italian: Integrating Components for the Analysis of Italian into a Multilingual Linguistic Complexity Analysis Tool](https://aclanthology.org/2020.lrec-1.880) (Okinina et al., LREC 2020)
ACL