Difference between revisions of "Syntactic Analogies (State of the art)"
Jump to navigation
Jump to search
(Created page with "* [http://research.microsoft.com/en-us/um/people/gzweig/Pubs/myz_naacl13_test_set.tgz Microsoft Research Syntactic Analogies Dataset] * A test set of analogy questions of the ...") |
|
(No difference)
| |
Revision as of 11:06, 28 April 2014
- Microsoft Research Syntactic Analogies Dataset
- A test set of analogy questions of the form "a is to b as c is to" testing
- base/comparative/superlative forms of adjectives
- singular/plural forms of common nouns
- possessive/non-possessive forms of common nouns
- base, past and 3rd person present tense forms of verbs
- Originally proposed in Mikolov et al. (2013)
- see also: Similarity (State of the art)
Table of results
- Listed in order of increasing accuracy
| Algorithm | Reference | Accuracy (%) |
|---|---|---|
| CW-100 | Mikolov et al. (2013) | 5.0 |
| HLBL-100 | Mikolov et al. (2013) | 18.7 |
| RNN-1600 | Mikolov et al. (2013) | 39.6 |
| vLBL+NCE5 | Mnih and Kavukcuoglu (2013) | 60.8 |
References
- Listed alphabetically.
Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. (2013). Linguistic regularities in continuous space word representations. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2013), Atlanta, Georgia.
Mnih, A. and Kavukcuoglu, K. (2013). Learning word embeddings efficiently with noise-contrastive estimation. In Advances in Neural Information Processing Systems (pp. 2265-2273).