@inproceedings{soler-wanner-2016-semi,
title = "A Semi-Supervised Approach for Gender Identification",
author = "Soler, Juan and
Wanner, Leo",
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/L16-1204",
pages = "1282--1287",
abstract = "In most of the research studies on Author Profiling, large quantities of correctly labeled data are used to train the models. However, this does not reflect the reality in forensic scenarios: in practical linguistic forensic investigations, the resources that are available to profile the author of a text are usually scarce. To pay tribute to this fact, we implemented a Semi-Supervised Learning variant of the k nearest neighbors algorithm that uses small sets of labeled data and a larger amount of unlabeled data to classify the authors of texts by gender (man vs woman). We describe the enriched KNN algorithm and show that the use of unlabeled instances improves the accuracy of our gender identification model. We also present a feature set that facilitates the use of a very small number of instances, reaching accuracies higher than 70{\%} with only 113 instances to train the model. It is also shown that the algorithm also performs well using publicly available data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soler-wanner-2016-semi">
<titleInfo>
<title>A Semi-Supervised Approach for Gender Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Soler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</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 most of the research studies on Author Profiling, large quantities of correctly labeled data are used to train the models. However, this does not reflect the reality in forensic scenarios: in practical linguistic forensic investigations, the resources that are available to profile the author of a text are usually scarce. To pay tribute to this fact, we implemented a Semi-Supervised Learning variant of the k nearest neighbors algorithm that uses small sets of labeled data and a larger amount of unlabeled data to classify the authors of texts by gender (man vs woman). We describe the enriched KNN algorithm and show that the use of unlabeled instances improves the accuracy of our gender identification model. We also present a feature set that facilitates the use of a very small number of instances, reaching accuracies higher than 70% with only 113 instances to train the model. It is also shown that the algorithm also performs well using publicly available data.</abstract>
<identifier type="citekey">soler-wanner-2016-semi</identifier>
<location>
<url>https://aclanthology.org/L16-1204</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1282</start>
<end>1287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semi-Supervised Approach for Gender Identification
%A Soler, Juan
%A Wanner, Leo
%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 soler-wanner-2016-semi
%X In most of the research studies on Author Profiling, large quantities of correctly labeled data are used to train the models. However, this does not reflect the reality in forensic scenarios: in practical linguistic forensic investigations, the resources that are available to profile the author of a text are usually scarce. To pay tribute to this fact, we implemented a Semi-Supervised Learning variant of the k nearest neighbors algorithm that uses small sets of labeled data and a larger amount of unlabeled data to classify the authors of texts by gender (man vs woman). We describe the enriched KNN algorithm and show that the use of unlabeled instances improves the accuracy of our gender identification model. We also present a feature set that facilitates the use of a very small number of instances, reaching accuracies higher than 70% with only 113 instances to train the model. It is also shown that the algorithm also performs well using publicly available data.
%U https://aclanthology.org/L16-1204
%P 1282-1287
Markdown (Informal)
[A Semi-Supervised Approach for Gender Identification](https://aclanthology.org/L16-1204) (Soler & Wanner, LREC 2016)
ACL
- Juan Soler and Leo Wanner. 2016. A Semi-Supervised Approach for Gender Identification. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1282–1287, Portorož, Slovenia. European Language Resources Association (ELRA).