@InProceedings{tu-gimpel-livescu:2017:RepL4NLP,
  author    = {Tu, Lifu  and  Gimpel, Kevin  and  Livescu, Karen},
  title     = {Learning to Embed Words in Context for Syntactic Tasks},
  booktitle = {Proceedings of the 2nd Workshop on Representation Learning for NLP},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {265--275},
  abstract  = {We present models for embedding words in the context of surrounding words. 
	Such models, which we refer to as token embeddings, represent the
	characteristics of a word that are specific to a given context, such as word
	sense, syntactic category, and semantic role. We explore simple, efficient
	token embedding models based on standard neural network architectures. We learn
	token embeddings on a large amount of unannotated text and evaluate them as
	features for part-of-speech taggers and dependency parsers trained on much
	smaller amounts of annotated data.  We find that predictors endowed with token
	embeddings consistently outperform baseline predictors across a range of
	context window and training set sizes.},
  url       = {http://www.aclweb.org/anthology/W17-2632}
}