@inproceedings{albogamy-ramsay-2016-fast,
title = "Fast and Robust {POS} tagger for {A}rabic Tweets Using Agreement-based Bootstrapping",
author = "Albogamy, Fahad and
Ramsay, Allan",
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/L16-1238",
pages = "1500--1506",
abstract = "Part-of-Speech(POS) tagging is a key step in many NLP algorithms. However, tweets are difficult to POS tag because they are short, are not always written maintaining formal grammar and proper spelling, and abbreviations are often used to overcome their restricted lengths. Arabic tweets also show a further range of linguistic phenomena such as usage of different dialects, romanised Arabic and borrowing foreign words. In this paper, we present an evaluation and a detailed error analysis of state-of-the-art POS taggers for Arabic when applied to Arabic tweets. On the basis of this analysis, we combine normalisation and external knowledge to handle the domain noisiness and exploit bootstrapping to construct extra training data in order to improve POS tagging for Arabic tweets. Our results show significant improvements over the performance of a number of well-known taggers for Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albogamy-ramsay-2016-fast">
<titleInfo>
<title>Fast and Robust POS tagger for Arabic Tweets Using Agreement-based Bootstrapping</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">Albogamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Allan</namePart>
<namePart type="family">Ramsay</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>Part-of-Speech(POS) tagging is a key step in many NLP algorithms. However, tweets are difficult to POS tag because they are short, are not always written maintaining formal grammar and proper spelling, and abbreviations are often used to overcome their restricted lengths. Arabic tweets also show a further range of linguistic phenomena such as usage of different dialects, romanised Arabic and borrowing foreign words. In this paper, we present an evaluation and a detailed error analysis of state-of-the-art POS taggers for Arabic when applied to Arabic tweets. On the basis of this analysis, we combine normalisation and external knowledge to handle the domain noisiness and exploit bootstrapping to construct extra training data in order to improve POS tagging for Arabic tweets. Our results show significant improvements over the performance of a number of well-known taggers for Arabic.</abstract>
<identifier type="citekey">albogamy-ramsay-2016-fast</identifier>
<location>
<url>https://aclanthology.org/L16-1238</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1500</start>
<end>1506</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast and Robust POS tagger for Arabic Tweets Using Agreement-based Bootstrapping
%A Albogamy, Fahad
%A Ramsay, Allan
%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 albogamy-ramsay-2016-fast
%X Part-of-Speech(POS) tagging is a key step in many NLP algorithms. However, tweets are difficult to POS tag because they are short, are not always written maintaining formal grammar and proper spelling, and abbreviations are often used to overcome their restricted lengths. Arabic tweets also show a further range of linguistic phenomena such as usage of different dialects, romanised Arabic and borrowing foreign words. In this paper, we present an evaluation and a detailed error analysis of state-of-the-art POS taggers for Arabic when applied to Arabic tweets. On the basis of this analysis, we combine normalisation and external knowledge to handle the domain noisiness and exploit bootstrapping to construct extra training data in order to improve POS tagging for Arabic tweets. Our results show significant improvements over the performance of a number of well-known taggers for Arabic.
%U https://aclanthology.org/L16-1238
%P 1500-1506
Markdown (Informal)
[Fast and Robust POS tagger for Arabic Tweets Using Agreement-based Bootstrapping](https://aclanthology.org/L16-1238) (Albogamy & Ramsay, LREC 2016)
ACL