Named Entity Recognition in Tweets: An Experimental Study

摘要: 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 standard NLP tools is severely degraded on tweets. This paper addresses this issue by re-building pipeline beginning with part-of-speech tagging, through chunking, to named-entity recognition. Our novel T-ner system doubles F1 score compared Stanford NER system. leverages redundancy inherent tweets achieve performance, using LabeledLDA exploit Freebase dictionaries as source distant supervision. outperforms co-training, increasing 25% over ten common entity types. Our are available at: http://github.com/aritter/twitter_nlp