@inproceedings{celebi-ozgur-2016-segmenting,
title = "Segmenting Hashtags using Automatically Created Training Data",
author = {{\c{C}}elebi, Arda and
{\"O}zg{\"u}r, Arzucan},
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/L16-1476",
pages = "2981--2985",
abstract = "Hashtags, which are commonly composed of multiple words, are increasingly used to convey the actual messages in tweets. Understanding what tweets are saying is getting more dependent on understanding hashtags. Therefore, identifying the individual words that constitute a hashtag is an important, yet a challenging task due to the abrupt nature of the language used in tweets. In this study, we introduce a feature-rich approach based on using supervised machine learning methods to segment hashtags. Our approach is unsupervised in the sense that instead of using manually segmented hashtags for training the machine learning classifiers, we automatically create our training data by using tweets as well as by automatically extracting hashtag segmentations from a large corpus. We achieve promising results with such automatically created noisy training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="celebi-ozgur-2016-segmenting">
<titleInfo>
<title>Segmenting Hashtags using Automatically Created Training Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Çelebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arzucan</namePart>
<namePart type="family">Özgür</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>Hashtags, which are commonly composed of multiple words, are increasingly used to convey the actual messages in tweets. Understanding what tweets are saying is getting more dependent on understanding hashtags. Therefore, identifying the individual words that constitute a hashtag is an important, yet a challenging task due to the abrupt nature of the language used in tweets. In this study, we introduce a feature-rich approach based on using supervised machine learning methods to segment hashtags. Our approach is unsupervised in the sense that instead of using manually segmented hashtags for training the machine learning classifiers, we automatically create our training data by using tweets as well as by automatically extracting hashtag segmentations from a large corpus. We achieve promising results with such automatically created noisy training data.</abstract>
<identifier type="citekey">celebi-ozgur-2016-segmenting</identifier>
<location>
<url>https://aclanthology.org/L16-1476</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2981</start>
<end>2985</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Segmenting Hashtags using Automatically Created Training Data
%A Çelebi, Arda
%A Özgür, Arzucan
%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 celebi-ozgur-2016-segmenting
%X Hashtags, which are commonly composed of multiple words, are increasingly used to convey the actual messages in tweets. Understanding what tweets are saying is getting more dependent on understanding hashtags. Therefore, identifying the individual words that constitute a hashtag is an important, yet a challenging task due to the abrupt nature of the language used in tweets. In this study, we introduce a feature-rich approach based on using supervised machine learning methods to segment hashtags. Our approach is unsupervised in the sense that instead of using manually segmented hashtags for training the machine learning classifiers, we automatically create our training data by using tweets as well as by automatically extracting hashtag segmentations from a large corpus. We achieve promising results with such automatically created noisy training data.
%U https://aclanthology.org/L16-1476
%P 2981-2985
Markdown (Informal)
[Segmenting Hashtags using Automatically Created Training Data](https://aclanthology.org/L16-1476) (Çelebi & Özgür, LREC 2016)
ACL