Abstract | ||
---|---|---|
We present a usage consultation tool based on Internet searching. When a user enters a string of words that he wants to find the usage for, the system sends a query to the search engine to obtain a corpus about the string. The corpus is statistically analyzed and results are displayed. As the system uses neither language-dependent analysis nor initial data, queries can be made in any language, even languages for which there are no well-established analytical methods. Also, since the corpus is dynamically obtained from the search engines, the usages provided to the user are always up to date. Kiwi can fill in the missing parts of the collocations frequently used by native speakers. |
Year | DOI | Venue |
---|---|---|
2003 | 10.3115/1075178.1075192 | ACL (Companion) |
Keywords | Field | DocType |
native speaker,usage consultation tool,missing part,initial data,language-dependent analysis,multilingual usage consultation tool,search engine,well-established analytical method,dependence analysis | World Wide Web,Search engine,Computer science,Artificial intelligence,Natural language processing,Delegation (computing),The Internet | Conference |
Volume | ISBN | Citations |
P03-2 | 0-111-456789 | 1 |
PageRank | References | Authors |
0.38 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kumiko Tanaka-Ishii | 1 | 261 | 36.69 |
Masato Yamamoto | 2 | 11 | 3.00 |
Hiroshi Nakagawa | 3 | 390 | 40.38 |