WordSimilarity-353 Test Collection (State of the art)
Revision as of 11:59, 3 October 2013 by Pdturney (talk | contribs) (moved WordSimilarity-353 Test Collection to WordSimilarity-353 Test Collection (State of the art))
- WordSimilarity-353 Test Collection
- contains two sets of English word pairs along with human-assigned similarity judgements
- first set (set1) contains 153 word pairs along with their similarity scores assigned by 13 subjects
- second set (set2) contains 200 word pairs with similarity assessed by 16 subjects
- WordSimilarity-353 dataset is available here
- performance is measured by Spearman's rank correlation coefficient
- introduced by Finkelstein et al. (2002)
- subsequently used by many other researchers
Table of results
- Listed in order of increasing Spearman's rho.
| Algorithm | Reference | Type | Spearman's rho |
|---|---|---|---|
| HSMN+csmRNN | Luong et al. (2013) | Corpus-based | 0.65 |
| ESA-Wikipedia | Gabrilovich and Markovitch (2007) | Hybrid | 0.75 |
References
Gabrilovich, Evgeniy, and Shaul Markovitch. (2007). Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis. In IJCAI, vol. 7, pp. 1606-1611.
Luong, Minh-Thang, Richard Socher, and Christopher D. Manning. (2013). Better word representations with recursive neural networks for morphology. CoNLL-2013: 104.