| tech,0-1-P06-1013,ak | As an educational tool , it has been used as part of a unit on protocol analysis in an Educational Research Methods course . <term> Combination methods </term> are an effective way of improving system performance . | #11905 As an educational tool, it has been used as part of a unit on protocol analysis in an Educational Research Methods course.Combination methods are an effective way of improving system performance. | |
| tech,9-2-P06-1013,ak | This paper examines the benefits of <term> system combination </term> for <term> unsupervised WSD </term> . | #11925 This paper examines the benefits of system combination forunsupervised WSD. | |
| other,12-4-P06-1013,ak | Our <term> combination methods </term> rely on predominant <term> senses </term> which are derived automatically from <term> raw text </term> . | #11958 Our combination methods rely on predominant senses which are derived automatically fromraw text. | |
| tech,6-2-P06-1013,ak | This paper examines the benefits of <term> system combination </term> for <term> unsupervised WSD </term> . | #11922 This paper examines the benefits ofsystem combination for unsupervised WSD. | |
| tech,14-3-P06-1013,ak | We investigate several <term> voting - and arbiter-based combination strategies </term> over a diverse pool of <term> unsupervised WSD systems </term> . | #11942 We investigate several voting- and arbiter-based combination strategies over a diverse pool ofunsupervised WSD systems. | |
| tech,1-4-P06-1013,ak | Our <term> combination methods </term> rely on predominant <term> senses </term> which are derived automatically from <term> raw text </term> . | #11947 Ourcombination methods rely on predominant senses which are derived automatically from raw text. | |
| other,11-5-P06-1013,ak | Experiments using the <term> SemCor and Senseval-3 data sets </term> demonstrate that our <term> ensembles </term> yield significantly better results when compared with state-of-the-art . | #11972 Experiments using the SemCor and Senseval-3 data sets demonstrate that ourensembles yield significantly better results when compared with state-of-the-art. | |
| other,6-4-P06-1013,ak | Our <term> combination methods </term> rely on predominant <term> senses </term> which are derived automatically from <term> raw text </term> . | #11952 Our combination methods rely on predominantsenses which are derived automatically from raw text. | |
| tech,3-3-P06-1013,ak | We investigate several <term> voting - and arbiter-based combination strategies </term> over a diverse pool of <term> unsupervised WSD systems </term> . | #11931 We investigate severalvoting - and arbiter-based combination strategies over a diverse pool of unsupervised WSD systems. | |
| lr-prod,3-5-P06-1013,ak | Experiments using the <term> SemCor and Senseval-3 data sets </term> demonstrate that our <term> ensembles </term> yield significantly better results when compared with state-of-the-art . | #11964 Experiments using theSemCor and Senseval-3 data sets demonstrate that our ensembles yield significantly better results when compared with state-of-the-art. |
