%0 Conference Paper %1 Ritter:2011:NER:2145432.2145595 %A Ritter, Alan %A Clark, Sam %A Mausam, %A Etzioni, Oren %B Proceedings of the Conference on Empirical Methods in Natural Language Processing %C Stroudsburg, PA, USA %D 2011 %I Association for Computational Linguistics %K ner phdproposal twitter %P 1524--1534 %T Named Entity Recognition in Tweets: An Experimental Study %U http://dl.acm.org/citation.cfm?id=2145432.2145595 %X People tweet more than 100 Million times daily, yielding a noisy, informal, but sometimes informative corpus of 140-character messages that mirrors the zeitgeist in an unprecedented manner. The performance of standard NLP tools is severely degraded on tweets. This paper addresses this issue by re-building the NLP pipeline beginning with part-of-speech tagging, through chunking, to named-entity recognition. Our novel T-ner system doubles F1 score compared with the Stanford NER system. T-ner leverages the redundancy inherent in tweets to achieve this performance, using LabeledLDA to exploit Freebase dictionaries as a source of distant supervision. LabeledLDA outperforms co-training, increasing F1 by 25% over ten common entity types. Our NLP tools are available at: http://github.com/aritter/twitter_nlp %@ 978-1-937284-11-4

@inproceedings{Ritter:2011:NER:2145432.2145595, abstract = {People tweet more than 100 Million times daily, yielding a noisy, informal, but sometimes informative corpus of 140-character messages that mirrors the zeitgeist in an unprecedented manner. The performance of standard NLP tools is severely degraded on tweets. This paper addresses this issue by re-building the NLP pipeline beginning with part-of-speech tagging, through chunking, to named-entity recognition. Our novel T-ner system doubles F1 score compared with the Stanford NER system. T-ner leverages the redundancy inherent in tweets to achieve this performance, using LabeledLDA to exploit Freebase dictionaries as a source of distant supervision. LabeledLDA outperforms co-training, increasing F1 by 25% over ten common entity types. Our NLP tools are available at: http://github.com/aritter/twitter_nlp}, acmid = {2145595}, added-at = {2015-01-23T10:54:17.000+0100}, address = {Stroudsburg, PA, USA}, author = {Ritter, Alan and Clark, Sam and Mausam and Etzioni, Oren}, biburl = {https://www.bibsonomy.org/bibtex/2bbc287fe4da02036bd2ef971a5d3aaaa/asmelash}, booktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing}, description = {Named entity recognition in tweets}, interhash = {3e3fe3a49491fcec718e78757730d6b7}, intrahash = {bbc287fe4da02036bd2ef971a5d3aaaa}, isbn = {978-1-937284-11-4}, keywords = {ner phdproposal twitter}, location = {Edinburgh, United Kingdom}, numpages = {11}, pages = {1524--1534}, publisher = {Association for Computational Linguistics}, series = {EMNLP '11}, timestamp = {2015-01-23T10:54:17.000+0100}, title = {Named Entity Recognition in Tweets: An Experimental Study}, url = {http://dl.acm.org/citation.cfm?id=2145432.2145595}, year = 2011 }