Approaches to convert RNNLM to BNLM - 版本历史

Lr：/* related algorithm */

2014-11-04T14:27:12Z

‎related algorithm

2014-11-04T13:41:03Z

‎related algorithm

2014-11-02T14:52:38Z

2014-11-02T07:41:33Z

‎related paper

2014-11-02T07:40:50Z

‎related paper

2014-11-02T07:40:22Z

‎related paper

2014-11-02T07:36:05Z

‎related paper

2014-11-02T07:34:32Z

‎related paper

2014-11-02T07:17:05Z

2014-11-02T06:29:19Z

@@ 第6行： / 第6行： @@
 * Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf?ip=166.111.134.19&id=2583722&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2E587F3204F5B62A59%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=593700348&CFTOKEN=42817565&__acm__=1414915690_c0bb48e7020d821b2f5841fa71632ebb]
 =related algorithm=
-* gibbs sampling[http://cos.name/2013/01/lda-math-mcmc-and-gibbs-sampling/]
+* gibbs sampling[http://cos.name/2013/01/lda-math-mcmc-and-gibbs-sampling/][http://www.xperseverance.net/blogs/tag/gibbs-sampling/]
 * Kullback–Leibler divergence[http://zh.wikipedia.org/wiki/%E7%9B%B8%E5%AF%B9%E7%86%B5]

←上一版本		2014年11月4日 (二) 13:41的版本
第7行：		第7行：
	=related algorithm=		=related algorithm=
	* gibbs sampling[http://cos.name/2013/01/lda-math-mcmc-and-gibbs-sampling/]		* gibbs sampling[http://cos.name/2013/01/lda-math-mcmc-and-gibbs-sampling/]
		+	* Kullback–Leibler divergence[http://zh.wikipedia.org/wiki/%E7%9B%B8%E5%AF%B9%E7%86%B5]

←上一版本		2014年11月2日 (日) 14:52的版本
第5行：		第5行：
	* Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]		* Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]
	* Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf?ip=166.111.134.19&id=2583722&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2E587F3204F5B62A59%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=593700348&CFTOKEN=42817565&__acm__=1414915690_c0bb48e7020d821b2f5841fa71632ebb]		* Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf?ip=166.111.134.19&id=2583722&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2E587F3204F5B62A59%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=593700348&CFTOKEN=42817565&__acm__=1414915690_c0bb48e7020d821b2f5841fa71632ebb]
		+	=related algorithm=
		+	* gibbs sampling[http://cos.name/2013/01/lda-math-mcmc-and-gibbs-sampling/]

@@ 第4行： / 第4行： @@
 * VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]
 * Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]
-*　Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf]
+* Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf?ip=166.111.134.19&id=2583722&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2E587F3204F5B62A59%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=593700348&CFTOKEN=42817565&__acm__=1414915690_c0bb48e7020d821b2f5841fa71632ebb]

@@ 第4行： / 第4行： @@
 * VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]
 * Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]
-*　Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf　ip=166.111.134.19&id=2583722&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2E587F3204F5B62A59%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=593700348&CFTOKEN=42817565&__acm__=1414915690_c0bb48e7020d821b2f5841fa71632ebb]
+*　Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition[http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf]

←上一版本		2014年11月2日 (日) 07:36的版本
第4行：		第4行：
	* VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]		* VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]
	* Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]		* Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]
		+	*　Converting Neural Network Language Models into　Back-off Language Models for Efﬁcient Decoding　in Automatic Speech Recognition［http://delivery.acm.org/10.1145/2590000/2583722/06645438.pdf?ip=166.111.134.19&id=2583722&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2E587F3204F5B62A59%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=593700348&CFTOKEN=42817565&__acm__=1414915690_c0bb48e7020d821b2f5841fa71632ebb］

←上一版本		2014年11月2日 (日) 07:34的版本
第3行：		第3行：
	=related paper=		=related paper=
	* VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]		* VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]
		+	* Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf]

←上一版本		2014年11月2日 (日) 07:17的版本
第1行：		第1行：
	=main paper=		=main paper=
	comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/31/IS140337.pdf]		comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/31/IS140337.pdf]
		+	=related paper=
		+	* VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1]

←上一版本		2014年11月2日 (日) 06:29的版本
第1行：		第1行：
−	=main paper==	+	=main paper=
	comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/31/IS140337.pdf]		comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/31/IS140337.pdf]