| Presentation | 2004/11/30 A Domain-Specific Concept-Based Searching System(Text Mining I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining) Tru H. Cao, Mai T.H. Ta, Tung Q. Luong, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Search engines are helpful tools for finding information from a large collection of electronic documents. However, current keyword-based engines, in which searching is basically to match the keywords in queries and those in documents, are not performing well in terms of the precision and recall criteria. The main reason is that, in natural language, one word can have different senses and different words can mean the same thing in particular contexts. This paper is to share our experience in developing a document searching system that aims at answering to "what a user means" rather than "what a user says". Here, queries and documents are abstracted into vectors of pre-defined concepts and, posed a query, the answers will be those documents whose concept vectors and that of the query have the smallest angles. It requires a corpus of specific knowledge about the concepts and their associated terms in a domain of discourse. Our chosen documents are about regulations of financial management in Vietnam. Experiments have shown that the implemented concept-based searching system outperforms traditional keyword-based ones. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | AI2004-53 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2004/11/30(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 | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Domain-Specific Concept-Based Searching System(Text Mining I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining) |
| Sub Title (in English) | |
| Keyword(1) | |
| 1st Author's Name | Tru H. Cao |
| 1st Author's Affiliation | Faculty of Information Technology Ho Chi Minh City University of Technology Viet Nam() |
| 2nd Author's Name | Mai T.H. Ta |
| 2nd Author's Affiliation | Faculty of Information Technology Ho Chi Minh City University of Technology Viet Nam |
| 3rd Author's Name | Tung Q. Luong |
| 3rd Author's Affiliation | Faculty of Information Technology Ho Chi Minh City University of Technology Viet Nam |
| Date | 2004/11/30 |
| Paper # | AI2004-53 |
| Volume (vol) | vol.104 |
| Number (no) | 488 |
| Page | pp.pp.- |
| #Pages | 4 |
| Date of Issue | |