@InProceedings{henry-cuffy-mcinnes:2017:BioNLP17,
  author    = {Henry, Sam  and  Cuffy, Clint  and  McInnes, Bridget},
  title     = {Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation},
  booktitle = {BioNLP 2017},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada,},
  publisher = {Association for Computational Linguistics},
  pages     = {272--281},
  abstract  = {In this paper, we present an analysis of feature extraction methods via
	dimensionality reduction for the task of biomedical Word Sense Disambiguation
	(WSD). We modify the vector representations in the 2-MRD WSD algorithm, and
	evaluate four dimensionality reduction methods: Word Embeddings using
	Continuous Bag of Words and Skip Gram, Singular Value Decomposition (SVD), and
	Principal Component Analysis (PCA). We also evaluate the effects of vector size
	on the performance of each of these methods. Results are evaluated on five
	standard evaluation datasets (Abbrev.100, Abbrev.200, Abbrev.300, NLM-WSD, and
	MSH-WSD). We find that vector sizes of 100 are sufficient for all techniques
	except SVD, for which a vector size of 1500 is referred. We also show that SVD
	performs on par with Word Embeddings for all but one dataset.},
  url       = {http://www.aclweb.org/anthology/W17-2334}
}