We address the problem of part-of-speech tagging for English data from the popular micro-blogging service Twitter. We develop a tagset, annotate data, develop features, and report tagging results nearing 90% accuracy. The data and tools have been made available to the research community with the goal of enabling richer text analysis of Twitter and related social media data sets.
%0 Conference Paper
%1 Gimpel:2011:PTT:2002736.2002747
%A Gimpel, Kevin
%A Schneider, Nathan
%A O'Connor, Brendan
%A Das, Dipanjan
%A Mills, Daniel
%A Eisenstein, Jacob
%A Heilman, Michael
%A Yogatama, Dani
%A Flanigan, Jeffrey
%A Smith, Noah A.
%B Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
%C Stroudsburg, PA, USA
%D 2011
%I Association for Computational Linguistics
%K pos solved tagging twitter web
%P 42--47
%T Part-of-speech tagging for Twitter: annotation, features, and experiments
%U http://dl.acm.org/citation.cfm?id=2002736.2002747
%X We address the problem of part-of-speech tagging for English data from the popular micro-blogging service Twitter. We develop a tagset, annotate data, develop features, and report tagging results nearing 90% accuracy. The data and tools have been made available to the research community with the goal of enabling richer text analysis of Twitter and related social media data sets.
%@ 978-1-932432-88-6
@inproceedings{Gimpel:2011:PTT:2002736.2002747,
abstract = {We address the problem of part-of-speech tagging for English data from the popular micro-blogging service Twitter. We develop a tagset, annotate data, develop features, and report tagging results nearing 90% accuracy. The data and tools have been made available to the research community with the goal of enabling richer text analysis of Twitter and related social media data sets.},
acmid = {2002747},
added-at = {2012-12-12T14:34:47.000+0100},
address = {Stroudsburg, PA, USA},
author = {Gimpel, Kevin and Schneider, Nathan and O'Connor, Brendan and Das, Dipanjan and Mills, Daniel and Eisenstein, Jacob and Heilman, Michael and Yogatama, Dani and Flanigan, Jeffrey and Smith, Noah A.},
biburl = {https://www.bibsonomy.org/bibtex/23efc79de4631cfd52ec207286c6ee703/jil},
booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2},
description = {Part-of-speech tagging for Twitter},
interhash = {577c820371cedfa9898cd83d0fe2da2b},
intrahash = {3efc79de4631cfd52ec207286c6ee703},
isbn = {978-1-932432-88-6},
keywords = {pos solved tagging twitter web},
location = {Portland, Oregon},
numpages = {6},
pages = {42--47},
publisher = {Association for Computational Linguistics},
series = {HLT '11},
timestamp = {2013-11-23T20:11:51.000+0100},
title = {Part-of-speech tagging for Twitter: annotation, features, and experiments},
url = {http://dl.acm.org/citation.cfm?id=2002736.2002747},
year = 2011
}