@InProceedings{yadav-EtAl:2017:EACLlong,
  author    = {Yadav, Shweta  and  Ekbal, Asif  and  Saha, Sriparna  and  Bhattacharyya, Pushpak},
  title     = {Entity Extraction in Biomedical Corpora: An Approach to Evaluate Word Embedding Features with PSO based Feature Selection},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {1159--1170},
  abstract  = {Text mining has drawn significant attention in recent past due to the rapid
	growth
	in biomedical and clinical records. Entity extraction is one of the fundamental
	components for biomedical text mining. In this paper, we propose a novel
	approach of feature selection for entity extraction that exploits the concept
	of deep learning and Particle Swarm Optimization (PSO). The system utilizes
	word embedding features along with several other features extracted by studying
	the properties of the datasets. We obtain an interesting observation that
	compact word embedding features as determined by PSO are more effective
	compared to the entire word embedding feature set for entity extraction. The
	proposed system is evaluated on three benchmark biomedical datasets such as
	GENIA, GENETAG, and AiMed. The effectiveness of the proposed approach is
	evident with significant performance gains over the baseline models as well as
	the other existing systems. We observe improvements of 7.86%, 5.27% and 7.25%
	F-measure points over the baseline models for GENIA, GENETAG, and AiMed dataset
	respectively.},
  url       = {http://www.aclweb.org/anthology/E17-1109}
}