@inproceedings{nazar-renau-2016-taxonomy,
title = "A Taxonomy of {S}panish Nouns, a Statistical Algorithm to Generate it and its Implementation in Open Source Code",
author = "Nazar, Rogelio and
Renau, Irene",
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/L16-1236/",
pages = "1485--1492",
abstract = "In this paper we describe our work in progress in the automatic development of a taxonomy of Spanish nouns, we offer the Perl implementation we have so far, and we discuss the different problems that still need to be addressed. We designed a statistically-based taxonomy induction algorithm consisting of a combination of different strategies not involving explicit linguistic knowledge. Being all quantitative, the strategies we present are however of different nature. Some of them are based on the computation of distributional similarity coefficients which identify pairs of sibling words or co-hyponyms, while others are based on asymmetric co-occurrence and identify pairs of parent-child words or hypernym-hyponym relations. A decision making process is then applied to combine the results of the previous steps, and finally connect lexical units to a basic structure containing the most general categories of the language. We evaluate the quality of the taxonomy both manually and also using Spanish Wordnet as a gold-standard. We estimate an average of 89.07{\%} precision and 25.49{\%} recall considering only the results which the algorithm presents with high degree of certainty, or 77.86{\%} precision and 33.72{\%} recall considering all results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nazar-renau-2016-taxonomy">
<titleInfo>
<title>A Taxonomy of Spanish Nouns, a Statistical Algorithm to Generate it and its Implementation in Open Source Code</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rogelio</namePart>
<namePart type="family">Nazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Renau</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>In this paper we describe our work in progress in the automatic development of a taxonomy of Spanish nouns, we offer the Perl implementation we have so far, and we discuss the different problems that still need to be addressed. We designed a statistically-based taxonomy induction algorithm consisting of a combination of different strategies not involving explicit linguistic knowledge. Being all quantitative, the strategies we present are however of different nature. Some of them are based on the computation of distributional similarity coefficients which identify pairs of sibling words or co-hyponyms, while others are based on asymmetric co-occurrence and identify pairs of parent-child words or hypernym-hyponym relations. A decision making process is then applied to combine the results of the previous steps, and finally connect lexical units to a basic structure containing the most general categories of the language. We evaluate the quality of the taxonomy both manually and also using Spanish Wordnet as a gold-standard. We estimate an average of 89.07% precision and 25.49% recall considering only the results which the algorithm presents with high degree of certainty, or 77.86% precision and 33.72% recall considering all results.</abstract>
<identifier type="citekey">nazar-renau-2016-taxonomy</identifier>
<location>
<url>https://aclanthology.org/L16-1236/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1485</start>
<end>1492</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Taxonomy of Spanish Nouns, a Statistical Algorithm to Generate it and its Implementation in Open Source Code
%A Nazar, Rogelio
%A Renau, Irene
%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 nazar-renau-2016-taxonomy
%X In this paper we describe our work in progress in the automatic development of a taxonomy of Spanish nouns, we offer the Perl implementation we have so far, and we discuss the different problems that still need to be addressed. We designed a statistically-based taxonomy induction algorithm consisting of a combination of different strategies not involving explicit linguistic knowledge. Being all quantitative, the strategies we present are however of different nature. Some of them are based on the computation of distributional similarity coefficients which identify pairs of sibling words or co-hyponyms, while others are based on asymmetric co-occurrence and identify pairs of parent-child words or hypernym-hyponym relations. A decision making process is then applied to combine the results of the previous steps, and finally connect lexical units to a basic structure containing the most general categories of the language. We evaluate the quality of the taxonomy both manually and also using Spanish Wordnet as a gold-standard. We estimate an average of 89.07% precision and 25.49% recall considering only the results which the algorithm presents with high degree of certainty, or 77.86% precision and 33.72% recall considering all results.
%U https://aclanthology.org/L16-1236/
%P 1485-1492
Markdown (Informal)
[A Taxonomy of Spanish Nouns, a Statistical Algorithm to Generate it and its Implementation in Open Source Code](https://aclanthology.org/L16-1236/) (Nazar & Renau, LREC 2016)
ACL