Named Entity Recognition from Scratch on Social Media

With the extensive amount of textual data flowing through social media platforms, the interest in Information Extraction (IE) on such textual data has increased. Named Entity Recognition (NER) is one of the basic problems of IE. State-of-the-art solutions for NER face an adaptation problem to informal texts from social media platforms. In this study, we addressed this generalization problem with the NLP from scratch idea that has been shown to be successful for several NLP tasks on formal text. Experimental results have shown that word embeddings can be successfully used for NER on informal text.

• Type: Journal
• Year: 2015
• Where: PKDD
• Authors: Kezban Dilek Kisa, Pinar Karagoz
• Keywords: Data Mining, PKDD 2015