Presentation | 2001/5/4 A Method of LR Table Compaction for Natural Language Processing and Speech Recognition Tomoyosi AKIBA, Katunobu ITOU, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper presents a method to reduce the number of states of the parsing table used for LR parsing algorithm. Particularly, it is intended to be used for natural language procesing and speech recognition. The proposed method can be implemented easily to both the existing LR table generation algorithm and the LR parsing algorithm, without making the parsing efficiency worse in theory. Our experimental results show that our method cut the number of states of LR table in half, and that the same result and efficiency is obtained by our method, as well as with the ordinary method, in both NLP and SR experiments. We also show several extensions of our method in order to apply it to the several extensional method of LR parsing, and iin order to reduce the number of states further. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Generalized LR Parsing / Parsing Table Compaction / Natural Language Processing / Speech Recognition |
Paper # | NLC2001-4 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2001/5/4(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) | A Method of LR Table Compaction for Natural Language Processing and Speech Recognition |
Sub Title (in English) | |
Keyword(1) | Generalized LR Parsing |
Keyword(2) | Parsing Table Compaction |
Keyword(3) | Natural Language Processing |
Keyword(4) | Speech Recognition |
1st Author's Name | Tomoyosi AKIBA |
1st Author's Affiliation | Information Technology Research Institute National Institute of Advanced Industrial Science and Technology() |
2nd Author's Name | Katunobu ITOU |
2nd Author's Affiliation | Information Technology Research Institute National Institute of Advanced Industrial Science and Technology |
Date | 2001/5/4 |
Paper # | NLC2001-4 |
Volume (vol) | vol.101 |
Number (no) | 40 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |