Annotating named entities in Twitter data with crowdsourcing
T. Finin, W. Murnane, A. Karandikar, N. Keller, J. Martineau, and M. Dredze. Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk, page 80--88. Stroudsburg, PA, USA, Association for Computational Linguistics, (2010)
Abstract
We describe our experience using both Amazon Mechanical Turk (MTurk) and Crowd-Flower to collect simple named entity annotations for Twitter status updates. Unlike most genres that have traditionally been the focus of named entity experiments, Twitter is far more informal and abbreviated. The collected annotations and annotation techniques will provide a first step towards the full study of named entity recognition in domains like Facebook and Twitter. We also briefly describe how to use MTurk to collect judgements on the quality of "word clouds."
%0 Conference Paper
%1 finin2010annotating
%A Finin, Tim
%A Murnane, Will
%A Karandikar, Anand
%A Keller, Nicholas
%A Martineau, Justin
%A Dredze, Mark
%B Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk
%C Stroudsburg, PA, USA
%D 2010
%I Association for Computational Linguistics
%K data entity recognition
%P 80--88
%T Annotating named entities in Twitter data with crowdsourcing
%U http://dl.acm.org/citation.cfm?id=1866696.1866709
%X We describe our experience using both Amazon Mechanical Turk (MTurk) and Crowd-Flower to collect simple named entity annotations for Twitter status updates. Unlike most genres that have traditionally been the focus of named entity experiments, Twitter is far more informal and abbreviated. The collected annotations and annotation techniques will provide a first step towards the full study of named entity recognition in domains like Facebook and Twitter. We also briefly describe how to use MTurk to collect judgements on the quality of "word clouds."
@inproceedings{finin2010annotating,
abstract = {We describe our experience using both Amazon Mechanical Turk (MTurk) and Crowd-Flower to collect simple named entity annotations for Twitter status updates. Unlike most genres that have traditionally been the focus of named entity experiments, Twitter is far more informal and abbreviated. The collected annotations and annotation techniques will provide a first step towards the full study of named entity recognition in domains like Facebook and Twitter. We also briefly describe how to use MTurk to collect judgements on the quality of "word clouds."},
acmid = {1866709},
added-at = {2013-01-25T16:32:04.000+0100},
address = {Stroudsburg, PA, USA},
author = {Finin, Tim and Murnane, Will and Karandikar, Anand and Keller, Nicholas and Martineau, Justin and Dredze, Mark},
biburl = {https://www.bibsonomy.org/bibtex/2f3ce5c15752dab9487220a3aae963655/schwemmlein},
booktitle = {Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk},
interhash = {0fa9636e69f2f516cdb6e11fffd8079b},
intrahash = {f3ce5c15752dab9487220a3aae963655},
keywords = {data entity recognition},
location = {Los Angeles, California},
numpages = {9},
pages = {80--88},
publisher = {Association for Computational Linguistics},
timestamp = {2013-01-25T16:32:04.000+0100},
title = {Annotating named entities in Twitter data with crowdsourcing},
url = {http://dl.acm.org/citation.cfm?id=1866696.1866709},
year = 2010
}