ontolog-forum
[Top] [All Lists]

Re: [ontolog-forum] Recurrent Neural Nets and Natural Language Models

To: "'[ontolog-forum]'" <ontolog-forum@xxxxxxxxxxxxxxxx>
From: "Rich Cooper" <metasemantics@xxxxxxxxxxxxxxxxxxxxxx>
Date: Thu, 5 Nov 2015 11:28:38 -0800
Message-id: <009d01d11800$2c4ff800$84efe800$@com>

Here is a quote from the thesis re the definition of "perplexity":

 

The notion "probability of a sentence" is an entirely useless one, under any known interpretation of this term. (Chomsky, 1969)

 

Still, we can consider entropy and perplexity as very useful measures. The simple reason is that in the real-world applications (such as speech recognizers), there is a strong positive correlation between perplexity of involved language model and the system's performance [24].

 

This comes from page 16 of the thesis. 

 

This is the English version of someone who is thinking in Czech.  Does anyone have a more usual interpretation of the word "perplexity" as it is being used here?  I don't recall Solomonoff using the term perplexity. 

 

Sincerely,

Rich Cooper,

Rich Cooper,

 

Chief Technology Officer,

MetaSemantics Corporation

MetaSemantics AT EnglishLogicKernel DOT com

( 9 4 9 ) 5 2 5-5 7 1 2

http://www.EnglishLogicKernel.com

 

From: Rich Cooper [mailto:metasemantics@xxxxxxxxxxxxxxxxxxxxxx]
Sent: Thursday, November 05, 2015 11:14 AM
To: '[ontolog-forum]'
Subject: Recurrent Neural Nets and Natural Language Models

 

Dear Ontologizers,

 

I have been looking for good explanations of how RNNs handle language, since there have been some recent advances in that area.  I found this dissertation described on the Corpora list, and it seems to be the clearest I have seen yet.  Its only 133 PDF pages; it's in paired Czech and English sections for those looking for parallel corpora; and it's intelligently written, at least the first few pages I have read. 

 

This is the dissertation:

 

http://www.fit.vutbr.cz/~imikolov/rnnlm/thesis.pdf

 

Sincerely,

Rich Cooper,

Rich Cooper,

 

Chief Technology Officer,

MetaSemantics Corporation

MetaSemantics AT EnglishLogicKernel DOT com

( 9 4 9 ) 5 2 5-5 7 1 2

http://www.EnglishLogicKernel.com

 


_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/  
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/  
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/ 
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J    (01)

<Prev in Thread] Current Thread [Next in Thread>
  • Re: [ontolog-forum] Recurrent Neural Nets and Natural Language Models, Rich Cooper <=