Empirical Comparisons of MASC Word Sense Annotations
Title | Empirical Comparisons of MASC Word Sense Annotations |
Publication Type | Conference Paper |
Year of Publication | 2012 |
Authors | de Melo, G., Baker C. F., Ide N., Passonneau R. J., & Fellbaum C. |
Other Numbers | 3278 |
Abstract | We analyze how different conceptions of lexical semantics affect sense annotations and how multiple sense inventories can be comparedempirically, based on annotated text. Our study focuses on the MASC project, where data has been annotated using WordNet senseidentifiers on the one hand, and FrameNet lexical units on the other. This allows us to compare the sense inventories of these lexicalresources empirically rather than just theoretically, based on their glosses, leading to new insights. In particular, we compute contingencymatrices and develop a novel measure, the Expected Jaccard Index, that quantifies the agreement between annotations of the same databased on two different resources even when they have different sets of categories. |
Acknowledgment | This work was partially funded by the Deutscher Akademischer Austausch Diesnst (DAAD) through a postdoctoral fellowship. |
URL | http://www.icsi.berkeley.edu/pubs/ai/empiricalcomparisons12.pdf |
Bibliographic Notes | Proceedings of the 8th Conference on International Language Resources and Evaluation (LREC 2012), Istanbul, Turkey |
Abbreviated Authors | G. de Melo, C. F. Baker, N. Ide, R. J. Passonneau, and C. Fellbaum |
ICSI Research Group | AI |
ICSI Publication Type | Article in conference proceedings |