Vira@FIRE 2015: Entity Extraction from Social Media Text Indian Languages (ESM-IL)

In this paper we have tried to identify and extract “Named Entities” from social media text using conditional random field(CRF) [3]. The paper represents our working methodology and result on Entity Extraction from Social Media Text Indian Languages task of FIRE-2015. We have extracted named entities from two languages Hindi and English. Named Entity Extraction system is implemented based on CRFSuite. CRFSuite [8] is the populer implementation of Conditional Random Fields (CRF). This is a sequential labelling task to achieve the desired tagging output. Conditional random fields (CRF) are a class of statistical modelling method often applied in pattern recognition, machine learning and many natural language processing tasks. We get F1-score of 19.82 and 3.72 for the Hindi and English text respectively.