@techreport{TD:100126,
	att_abstract={{State-of-the-art probabilistic models of text such as n-grams require an exponential number of examples as the size of the context grows, a problem that is due to the discrete word representation. We propose to solve this problem by learning a continuous-valued and low-dimensional mapping of words, and base our predictions for the probabilities of the target word on non-linear dynamics of the latent space representation of the words in context window. We build on neural networks-based language models; by expressing them as energy-based models, we can further enrich the models with additional inputs such as part-of-speech tags, topic information and graphs of word similarity. We demonstrate a significantly lower perplexity on different text corpora, as well as improved word accuracy rate on speech recognition tasks, as compared to Kneser-Ney back-off n-gram-based language models.}},
	att_authors={sc984q, sb799t, sb7658},
	att_categories={C_CCF.5, C_CCF.9, C_CCF.2, C_IIS.4, C_IIS.11, C_IIS.2},
	att_copyright={{IEEE}},
	att_copyright_notice={{}},
	att_donotupload={true},
	att_private={false},
	att_projects={},
	att_tags={Natural Language Processing, Speech Recognition, Continuous Distributed Representation, Neural Networks},
	att_techdoc={true},
	att_techdoc_key={TD:100126},
	att_url={},
	author={Sumit Chopra and Piotr Mirowski and Suhrid Balakrishnan and Srinivas Bangalore},
	institution={{IEEE Workshop on Spoken Language Technology}},
	month={December},
	title={{FEATURE-RICH CONTINUOUS LANGUAGE MODELS FOR SPEECH RECOGNITION}},
	year=2010,
}