STRUCTURED DISCRIMINATIVE MODELS USING DEEP NEURAL-NETWORK FEATURES R. C. van Dalen, J. Yang, H. Wang, A. Ragni, C. Zhang, M. J. F. Gales Department of Engineering, University of Cambridge, United Kingdom In this paper,

First Page		Document Content
Date: 2016-03-11 05:30:19 Markov models Machine learning Artificial intelligence Learning Computational linguistics Speech recognition software Computer accessibility Speech recognition Hidden Markov model Conditional random field Language model Image segmentation		STRUCTURED DISCRIMINATIVE MODELS USING DEEP NEURAL-NETWORK FEATURES R. C. van Dalen, J. Yang, H. Wang, A. Ragni, C. Zhang, M. J. F. Gales Department of Engineering, University of Cambridge, United Kingdom In this paper, Add to Reading List Source URL: mi.eng.cam.ac.uk Download Document from Source Website File Size: 288,03 KB Share Document on Facebook

	Multi-source annotation projection of coreference chains: assessing strategies and testing opportunities Yulia Grishina and Manfred Stede Applied Computational Linguistics FSP Cognitive Science University of Potsdam DocID: 1vrep - View Document
	Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, July 2002, pp. DocID: 1vn1Q - View Document
	NODALIDA 2009 th 17 Nordic Conference of Computational Linguistics Kristiina Jokinen DocID: 1vkzQ - View Document
	Concepts and properties in word spaces* Marco Baroni & Alessandro Lenci Properties play a central role in most theories of conceptual knowledge. Since computational models derived from word co-occurrence statistics have DocID: 1vcjQ - View Document
	The ACL Anthology Reference Corpus: A Reference Dataset for Bibliographic Research in Computational Linguistics Steven Bird1 , Robert Dale2 , Bonnie J. Dorr3 , Bryan Gibson4 , Mark T. Joseph4 , Min-Yen Kan5† , Dongwon DocID: 1v63z - View Document