Name
Abstract | ||
|---|---|---|
This paper describes a novel, unsupervised method of word sense disambiguation that is wholly se- mantic, drawing upon a complex, rich ontology and inference engine (the Cyc system). This method goes beyond more familiar semantic closeness ap- proaches to disambiguation that rely on string co- occurrence or relative location in a taxonomy or concept map by 1) exploiting a rich array of prop- erties, including higher-order properties, not avail- able in merely taxonomic (or other first-order) sys- tems, and 2) appealing to the semantic contribution a word sense makes to the content of the target text. Experiments show that this method produces results markedly better than chance when disam- biguating word senses in a corpus of topically un- related documents. |
Year | Venue | Keywords |
|---|---|---|
2006 | FLAIRS Conference | higher order,first order,concept map |
Field | DocType | Citations |
Ontology,SemEval,Computer science,Artificial intelligence,Natural language processing,Word-sense disambiguation | Conference | 19 |
PageRank | References | Authors |
1.38 | 4 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jon Curtis | 1 | 419 | 24.88 |
| John Cabral | 2 | 253 | 17.95 |
| David Baxter | 3 | 72 | 7.31 |