Presentation 1997/12/12
Natural Language Models Based on Repetitional String
Hiroki Mori, Hirotomo Aso, Shozo Makino,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, a new, knowledge-free language model with great ability in reducing ambiguity. This model is defined as n-gram of string which is referred to "superword," and belongs to a superclass of traditional word or string n-gram models' class. The concept of superword is based on only one principle-repetitionality in training text. The probabilistic distribution of the model is learned through the forward-backward algorithm. Experimental results showed that the performance of superword model combined with character trigram model was superior to the traditional word model based on morphological analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) language model / superword / n-gram / speech recognition / character recognition
Paper # NLC97-47
Date of Issue

Conference Information
Committee NLC
Conference Date 1997/12/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Natural Language Models Based on Repetitional String
Sub Title (in English)
Keyword(1) language model
Keyword(2) superword
Keyword(3) n-gram
Keyword(4) speech recognition
Keyword(5) character recognition
1st Author's Name Hiroki Mori
1st Author's Affiliation Graduate School of Engineering, Tohoku University()
2nd Author's Name Hirotomo Aso
2nd Author's Affiliation Graduate School of Engineering, Tohoku University
3rd Author's Name Shozo Makino
3rd Author's Affiliation Computer Center, Tohoku University
Date 1997/12/12
Paper # NLC97-47
Volume (vol) vol.97
Number (no) 440
Page pp.pp.-
#Pages 6
Date of Issue