Paper: The Effect of Ambiguity on the Automated Acquisition of WSD Examples

ACL ID N10-1053
Title The Effect of Ambiguity on the Automated Acquisition of WSD Examples
Venue Human Language Technologies
Session Main Conference
Year 2010
Authors

Several methods for automatically gen- erating labeled examples that can be used as training data for WSD systems have been proposed, including a semi- supervised approach based on relevance feedback(Stevenson et al., 2008a). This approachwas shown to generateexamples that improved the performanceof a WSD systemfor a set of ambiguoustermsfrom the biomedicaldomain.However, we find thatthisapproachdoesnotperformas well on other data sets. The levels of ambigu- ity in these data sets are analysedand we suggestthis is the reasonfor this negative result.