Named Entity Extraction and Linking Challenge: University of Twente at #Microposts2014
Mena Badieh Habib, Maurice van Keulen, Zhemin Zhu, Matthew Rowe, Milan Stanković, Aba‐Sah Dadzie · University of Twente Research Information · 2014
Twitter is a potentially rich source of continuously and instantly updated information. Shortness and informality of tweets are chal-lenges for Natural Language Processing (NLP) tasks. In this paper we present a hybrid approach for Named Entity Extraction (NEE) and Linking (NEL) for tweets. Although NEE and NEL are two topics that are well studied in literature, almost all approaches treated the two problems separately. We believe that disambiguation (link-ing) could help improving the extraction process. We call this po-tential for mutual improvement, the reinforcement effect. It mim-ics the way humans understand natural language. Furthermore, our proposed approaches handles uncertainties involved in the two pro-cesses by considering possible alternatives.