| lr,13-2-P95-1025,ak | which overcomes this problem using <term> | dictionary definitions | </term> . Using the <term> definition-based | #27745 In this paper, we describe an approach which overcomes this problem usingdictionary definitions. | |
| lr-prod,11-3-P95-1025,ak | collected from the relatively small <term> | Brown corpus | </term> , our <term> sense disambiguation system | #27759 Using the definition-based conceptual co-occurrence data collected from the relatively smallBrown corpus, our sense disambiguation system achieves an average accuracy comparable to human performance given the same contextual information. | |
| measure(ment),20-3-P95-1025,ak | disambiguation system </term> achieves an <term> | average accuracy | </term> comparable to <term> human performance | #27768 Using the definition-based conceptual co-occurrence data collected from the relatively small Brown corpus, our sense disambiguation system achieves anaverage accuracy comparable to human performance given the same contextual information. | |
| measure(ment),24-3-P95-1025,ak | average accuracy </term> comparable to <term> | human performance | </term> given the same <term> contextual information | #27772 Using the definition-based conceptual co-occurrence data collected from the relatively small Brown corpus, our sense disambiguation system achieves an average accuracy comparable tohuman performance given the same contextual information. | |
| other,17-1-P95-1025,ak | </term> , suffer from the problem of <term> | data sparseness | </term> . In this paper , we describe an | #27729 Corpus-based sense disambiguation methods, like most other statistical NLP approaches, suffer from the problem ofdata sparseness. | |
| other,2-3-P95-1025,ak | dictionary definitions </term> . Using the <term> | definition-based conceptual co-occurrence data | </term> collected from the relatively small | #27750 Using thedefinition-based conceptual co-occurrence data collected from the relatively small Brown corpus, our sense disambiguation system achieves an average accuracy comparable to human performance given the same contextual information. | |
| other,29-3-P95-1025,ak | human performance </term> given the same <term> | contextual information | </term> . We present a <term> corpus-based | #27777 Using the definition-based conceptual co-occurrence data collected from the relatively small Brown corpus, our sense disambiguation system achieves an average accuracy comparable to human performance given the samecontextual information. | |
| tech,0-1-P95-1025,ak | </term> and <term> foot nodes </term> . <term> | Corpus-based sense disambiguation methods | </term> , like most other <term> statistical | #27712 Our objectives are met by giving clear definitions that determine the projection of structures from the lexicon, and identify maximal projections, auxiliary trees and foot nodes.Corpus-based sense disambiguation methods, like most other statistical NLP approaches, suffer from the problem of data sparseness. | |
| tech,15-3-P95-1025,ak | small <term> Brown corpus </term> , our <term> | sense disambiguation system | </term> achieves an <term> average accuracy | #27763 Using the definition-based conceptual co-occurrence data collected from the relatively small Brown corpus, oursense disambiguation system achieves an average accuracy comparable to human performance given the same contextual information. | |
| tech,8-1-P95-1025,ak | disambiguation methods </term> , like most other <term> | statistical NLP approaches | </term> , suffer from the problem of <term> | #27720 Corpus-based sense disambiguation methods, like most otherstatistical NLP approaches, suffer from the problem of data sparseness. |
