@inproceedings{outahajala-rosso-2016-using,
title = "Using a Small Lexicon with {CRF}s Confidence Measure to Improve {POS} Tagging Accuracy",
author = "Outahajala, Mohamed and
Rosso, Paolo",
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/L16-1683",
pages = "4311--4315",
abstract = "Like most of the languages which have only recently started being investigated for the Natural Language Processing (NLP) tasks, Amazigh lacks annotated corpora and tools and still suffers from the scarcity of linguistic tools and resources. The main aim of this paper is to present a new part-of-speech (POS) tagger based on a new Amazigh tag set (AMTS) composed of 28 tags. In line with our goal we have trained Conditional Random Fields (CRFs) to build a POS tagger for the Amazigh language. We have used the 10-fold technique to evaluate and validate our approach. The CRFs 10 folds average level is 87.95{\%} and the best fold level result is 91.18{\%}. In order to improve this result, we have gathered a set of about 8k words with their POS tags. The collected lexicon was used with CRFs confidence measure in order to have a more accurate POS-tagger. Hence, we have obtained a better performance of 93.82{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="outahajala-rosso-2016-using">
<titleInfo>
<title>Using a Small Lexicon with CRFs Confidence Measure to Improve POS Tagging Accuracy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Outahajala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Rosso</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>Like most of the languages which have only recently started being investigated for the Natural Language Processing (NLP) tasks, Amazigh lacks annotated corpora and tools and still suffers from the scarcity of linguistic tools and resources. The main aim of this paper is to present a new part-of-speech (POS) tagger based on a new Amazigh tag set (AMTS) composed of 28 tags. In line with our goal we have trained Conditional Random Fields (CRFs) to build a POS tagger for the Amazigh language. We have used the 10-fold technique to evaluate and validate our approach. The CRFs 10 folds average level is 87.95% and the best fold level result is 91.18%. In order to improve this result, we have gathered a set of about 8k words with their POS tags. The collected lexicon was used with CRFs confidence measure in order to have a more accurate POS-tagger. Hence, we have obtained a better performance of 93.82%.</abstract>
<identifier type="citekey">outahajala-rosso-2016-using</identifier>
<location>
<url>https://aclanthology.org/L16-1683</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4311</start>
<end>4315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using a Small Lexicon with CRFs Confidence Measure to Improve POS Tagging Accuracy
%A Outahajala, Mohamed
%A Rosso, Paolo
%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 outahajala-rosso-2016-using
%X Like most of the languages which have only recently started being investigated for the Natural Language Processing (NLP) tasks, Amazigh lacks annotated corpora and tools and still suffers from the scarcity of linguistic tools and resources. The main aim of this paper is to present a new part-of-speech (POS) tagger based on a new Amazigh tag set (AMTS) composed of 28 tags. In line with our goal we have trained Conditional Random Fields (CRFs) to build a POS tagger for the Amazigh language. We have used the 10-fold technique to evaluate and validate our approach. The CRFs 10 folds average level is 87.95% and the best fold level result is 91.18%. In order to improve this result, we have gathered a set of about 8k words with their POS tags. The collected lexicon was used with CRFs confidence measure in order to have a more accurate POS-tagger. Hence, we have obtained a better performance of 93.82%.
%U https://aclanthology.org/L16-1683
%P 4311-4315
Markdown (Informal)
[Using a Small Lexicon with CRFs Confidence Measure to Improve POS Tagging Accuracy](https://aclanthology.org/L16-1683) (Outahajala & Rosso, LREC 2016)
ACL