[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

• ÚFAL Wiki Home
• ÚFAL Home
• Sitemap
• RSS
• ÚFAL calendar
• Recent changes
• Login
• Hledat:

[ Back to the navigation ]

Differences

This shows you the differences between two versions of the page.

View differences: Side by SideInline Go

Link to this comparison view

Both sides previous revision Previous revision 2012/03/12 22:59 longdt 2012/03/12 22:53 longdt 2012/03/12 22:53 longdt 2012/03/12 22:51 longdt 2012/03/12 22:50 longdt 2012/03/12 22:50 longdt 2012/03/12 22:49 longdt 2012/03/12 22:47 longdt 2012/03/12 22:45 longdt 2012/03/12 22:44 longdt 2012/03/12 22:42 longdt 2012/03/12 22:41 longdt 2012/03/12 22:41 longdt 2012/03/12 22:39 longdt 2012/03/12 20:22 longdt 2012/03/12 20:21 longdt 2012/03/12 20:19 longdt 2012/03/12 20:17 longdt 2012/03/12 20:16 longdt 2012/03/12 20:11 longdt vytvořeno Go Next revision		Previous revision 2012/03/12 22:59 longdt 2012/03/12 22:53 longdt 2012/03/12 22:53 longdt 2012/03/12 22:51 longdt 2012/03/12 22:50 longdt 2012/03/12 22:50 longdt 2012/03/12 22:49 longdt 2012/03/12 22:47 longdt 2012/03/12 22:45 longdt 2012/03/12 22:44 longdt 2012/03/12 22:42 longdt 2012/03/12 22:41 longdt 2012/03/12 22:41 longdt 2012/03/12 22:39 longdt 2012/03/12 20:22 longdt 2012/03/12 20:21 longdt 2012/03/12 20:19 longdt 2012/03/12 20:17 longdt 2012/03/12 20:16 longdt 2012/03/12 20:11 longdt vytvořeno Go Next revision Both sides next revision
courses:rg:2012:longdtreport [2012/03/12 20:19] longdt		courses:rg:2012:longdtreport [2012/03/12 22:45] longdt
Line 1:		Line 1:
	====== Faster and Smaller N-Gram Language Model ======		====== Faster and Smaller N-Gram Language Model ======
	//Presenter :  Joachim Daiber		//Presenter :  Joachim Daiber
-	Subscriber : Long DT//	+	Reporter: Long DT//
	Date : 12-March-2012\\		Date : 12-March-2012\\
	==== Overview ====		==== Overview ====
-	The talk is mainly about technique to improve performance of N-gram language model.	+	The talk is mainly about techniques to improve performance of N-gram language model.
	How it will run faster and use smaller amount of memory.		How it will run faster and use smaller amount of memory.
-	==== Notes ====	+	==== Encoding ====
		+	**I. Encoding the count**
		+	In web1T corpus, the most frequent n-gram is 95 billion times, but contain only 770 000 unique count.
		+	=> Maintain value rank array is a good way to encode count
		+	**II. Encoding the n-gram**
		+	**//Idea//**
		+	encode W1,W2....Wn = c(W1,W2...W(n-1)) Wn
		+	c is offset function, so call context encoding
		+
		+	**//Implementation//**
		+
		+	Sorted Array
		+	+ Use n array for n-gram model (array i-th is used for i-gram)
		+	+ Each element in array in pair (w,c)
		+	+ w : index of that word in unigram array
		+	+ c : offset pointer
		+	+ Sort base on w
		+	Improvement : Implicitly encode W (all n-gram ending with particular word wi are stored -> wasteful. So, maintain another array save the beginning and the end of the range
		+
		+	Hash Table
		+
	Most of the attendants apparently understood the talk and the paper well, and a		Most of the attendants apparently understood the talk and the paper well, and a
	lively discussion followed. One of our first topics of debate was the notion of		lively discussion followed. One of our first topics of debate was the notion of

---

[ Back to the navigation ] [ Back to the content ]