| Presentation | 1999/3/5 A Topic Recognition System of Spoken Dialogue Based on Thesaurus Information Shunsuke Iguchi, Nobuhiko Ogura, Sumio Watanabe, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a topic recognition method under spoken dialogue between a human and a computer, as a basic technology of spoken dialogue system. First, we compose a layered network of words which represents thesaurus relation to topic words, named thesaurus network. The thesaurus network has three parameters that are attached to three meanings of words; synonym, related word, and narrow sense word, These three parameters mean relational strength. Second, we calculate the sum of the weights of the word queue that is the result of speech recognition. Comparing this value, our system can recognize the topic of input sentence. We evaluate the result of recognition inputting sentences in the article of newspapers, and we also evaluate the optimization of parameters of the thesaurus network. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | / thesaurus network / maximum likelihood method / Kullback infomation / probabilistic scan method |
| Paper # | AI98-88 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 1999/3/5(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 | Artificial Intelligence and Knowledge-Based Processing (AI) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Topic Recognition System of Spoken Dialogue Based on Thesaurus Information |
| Sub Title (in English) | |
| Keyword(1) | |
| Keyword(2) | / thesaurus network |
| Keyword(3) | maximum likelihood method |
| Keyword(4) | Kullback infomation |
| Keyword(5) | probabilistic scan method |
| 1st Author's Name | Shunsuke Iguchi |
| 1st Author's Affiliation | Precision and Intelligence Laboratory Tokyo Institute of Technology() |
| 2nd Author's Name | Nobuhiko Ogura |
| 2nd Author's Affiliation | Precision and Intelligence Laboratory Tokyo Institute of Technology |
| 3rd Author's Name | Sumio Watanabe |
| 3rd Author's Affiliation | Precision and Intelligence Laboratory Tokyo Institute of Technology |
| Date | 1999/3/5 |
| Paper # | AI98-88 |
| Volume (vol) | vol.98 |
| Number (no) | 635 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |