Presentation | 1995/12/15 Back-off Method for N-gram Smoothing based on Binomial Posteriori Distribution Takeshi KAWABATA, Masafumi TAMOTO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The n-gram language models are powerful for treating natural spoken languages, however need large amounts of spoken language corpus for estimating reliable model parameters. For estimating n-gram probabilities from sparse data, Katz's back-off smoothing method is promising. However, this approach is sometimes unstable because it uses singleton heuristics based on Turing's formula. This paper proposes a new back-off method based on Binomial Posteriori Distribution of n-gram probabilities, which achieves stable and more effective n-gram smoothing by sophisticated calculation formula with no heuristics. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Natural language / n-gram / back-off / JUNO |
Paper # | NLC95-58,SP95-93 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 1995/12/15(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) | Back-off Method for N-gram Smoothing based on Binomial Posteriori Distribution |
Sub Title (in English) | |
Keyword(1) | Natural language |
Keyword(2) | n-gram |
Keyword(3) | back-off |
Keyword(4) | JUNO |
1st Author's Name | Takeshi KAWABATA |
1st Author's Affiliation | NTT Basic Research Laboratories() |
2nd Author's Name | Masafumi TAMOTO |
2nd Author's Affiliation | NTT Basic Research Laboratories |
Date | 1995/12/15 |
Paper # | NLC95-58,SP95-93 |
Volume (vol) | vol.95 |
Number (no) | 429 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |