| Presentation | 2003/5/22 Word Sense Discrimination based on complete N-partite graph Hidekazu NAKAWATASE, Akiko AIZAWA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper presents a method for discovering polysemic words. This method is based on extracting of maximal complete N-partite graphs from a N-partite graph corresponding to relations of words in a corpus. Those relations are obtained by the morphological analysis etc. And the extracted graphs as clusters of words are merged on some conditions. Consequently, a certain word that is polysemous belongs to two or more classifications. We experimented in order to check this clustering eifect. As a result of the this experiment, we obtained the 531 polysemy candidates from the graph which includes 30,000 nodes (words) - 20 words were actually polysemies among those. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | natural language / semantics / polysemy / N-partite graph |
| Paper # | AI2003-2 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2003/5/22(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) | Word Sense Discrimination based on complete N-partite graph |
| Sub Title (in English) | |
| Keyword(1) | natural language |
| Keyword(2) | semantics |
| Keyword(3) | polysemy |
| Keyword(4) | N-partite graph |
| 1st Author's Name | Hidekazu NAKAWATASE |
| 1st Author's Affiliation | The Graduate University for advanced studies() |
| 2nd Author's Name | Akiko AIZAWA |
| 2nd Author's Affiliation | National Institute of Information |
| Date | 2003/5/22 |
| Paper # | AI2003-2 |
| Volume (vol) | vol.103 |
| Number (no) | 103 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |