creators_name: Ashwini, Sandeep creators_name: Choi, Jinho D. creators_id: asandee@amazon.com creators_id: choi@mathcs.emory.edu type: preprint datestamp: 2014-08-24 20:59:40 lastmod: 2015-04-20 11:40:32 metadata_visibility: show title: Targetable Named Entity Recognition in Social Media ispublished: unpub subjects: comp-sci-lang subjects: ling-compara full_text_status: public abstract: We present a novel approach for recognizing what we call targetable named entities; that is, named entities in a targeted set (e.g, movies, books, TV shows). Unlike many other NER systems that need to retrain their statistical models as new entities arrive, our approach does not require such retraining, which makes it more adaptable for types of entities that are frequently updated. For this preliminary study, we focus on one entity type, movie title, using data collected from Twitter. Our system is tested on two evaluation sets, one including only entities corresponding to movies in our training set, and the other excluding any of those entities. Our final model shows F1-scores of 76.19% and 78.70% on these evaluation sets, which gives strong evidence that our approach is completely unbiased to any particular set of entities found during training. date: 2014-07-31 date_type: completed institution: Emory University department: Mathematics and Computer Science refereed: FALSE citation: Ashwini, Sandeep and Choi, Jinho D. (2014) Targetable Named Entity Recognition in Social Media. [Preprint] (Unpublished) document_url: http://cogprints.org/9764/1/cogprints2014a.pdf