Improving Twitter Named Entity Recognition using Word Representations

Zhiqiang Toh, Bin Chen, Jian Su
2015 Proceedings of the Workshop on Noisy User-generated Text  
This paper describes our system used in the ACL 2015 Workshop on Noisy Usergenerated Text Shared Task for Named Entity Recognition (NER) in Twitter. Our system uses Conditional Random Fields to train two separate classifiers for the two evaluations: predicting 10 fine-grained types, and segmenting named entities. We focus our efforts on generating word representations from large amount of unlabeled newswire data and tweets. Our experiment results show that cluster features derived from word
more » ... esentations significantly improve Twitter NER performances. Our system is ranked 2nd for both evaluations.
doi:10.18653/v1/w15-4321 dblp:conf/aclnut/TohCS15 fatcat:di3hsjjlkfd7jbyigoihn6lajq