| other,6-1-H92-1045,ak | </term> . It is well-known that there are <term> | polysemous words | </term> like <term> sentence </term> whose <term> | #24131 It is well-known that there arepolysemous words like sentence whose meaning or sense depends on the context of use. | |
| other,17-1-H92-1045,ak | or <term> sense </term> depends on the <term> | context of use | </term> . We have recently reported on two | #24142 It is well-known that there are polysemous words like sentence whose meaning or sense depends on thecontext of use. | |
| tech,7-2-H92-1045,ak | have recently reported on two new <term> | word-sense disambiguation systems | </term> , one trained on bilingual material | #24153 We have recently reported on two newword-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). | |
| lr-prod,18-2-H92-1045,ak | trained on bilingual material ( the <term> | Canadian Hansards | </term> ) and the other trained on monolingual | #24164 We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (theCanadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). | |
| lr-prod,29-2-H92-1045,ak | trained on monolingual material ( <term> | Roget 's Thesaurus | </term> and <term> Grolier 's Encyclopedia </term> | #24175 We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget 's Thesaurus and Grolier's Encyclopedia). | |
| lr-prod,33-2-H92-1045,ak | <term> Roget 's Thesaurus </term> and <term> | Grolier 's Encyclopedia | </term> ) . As this work was nearing completion | #24179 We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus andGrolier 's Encyclopedia). | |
| other,12-3-H92-1045,ak | completion , we observed a very strong <term> | discourse effect | </term> . That is , if a <term> polysemous | #24196 As this work was nearing completion, we observed a very strongdiscourse effect. | |
| other,5-4-H92-1045,ak | discourse effect </term> . That is , if a <term> | polysemous word | </term> such as <term> sentence </term> appears | #24204 That is, if apolysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense. | |
| tech,17-6-H92-1045,ak | for improving the performance of the <term> | word-sense disambiguation algorithm | </term> . In addition , it could also be | #24278 This result can be used as an additional source of constraint for improving the performance of theword-sense disambiguation algorithm. | |
| tech,11-7-H92-1045,ak | could also be used to help evaluate <term> | disambiguation algorithms | </term> that did not make use of the <term> | #24293 In addition, it could also be used to help evaluatedisambiguation algorithms that did not make use of the discourse constraint. | |
| model,20-7-H92-1045,ak | </term> that did not make use of the <term> | discourse constraint | </term> . This paper describes an extension | #24302 In addition, it could also be used to help evaluate disambiguation algorithms that did not make use of thediscourse constraint. |
