@techreport{TD:100254,
	att_abstract={{Distributed representations of words are attractive since they provide a means for measuring word similarity. However, most approaches to learning distributed representations are divorced from the task context. In this paper, we describe a model that learns distributed representations of words in order to optimize task performance. We investigate this model for part-of-speech tagging and supertagging tasks and demonstrate its superior accuracy over localist models, especially for rare words. We also show that adding non-linearity in the model aids in improved accuracy for complex tasks such as supertagging.             }},
	att_authors={sc984q, sb7658},
	att_categories={C_CCF.5, C_CCF.2, C_IIS.4},
	att_copyright={{IEEE}},
	att_copyright_notice={{}},
	att_donotupload={true},
	att_private={false},
	att_projects={},
	att_tags={Deep Learning,  Neural Networks,  Natural Language Processing,  Part-of-Speech tagging,  Super-tagging,  Latent  Representation },
	att_techdoc={true},
	att_techdoc_key={TD:100254},
	att_url={},
	author={Sumit Chopra and Srinivas Bangalore},
	institution={{The 36th International Conference on Acoustics, Speech and Signal Processing }},
	month={May},
	title={{NON-LINEAR TAGGING MODELS WITH LOCALIST AND DISTRIBUTED WORD REPRESENTATIONS}},
	year=2011,
}