Difference between revisions of "Syntactic Analogies (State of the art)"
Jump to navigation
Jump to search
(Wikidata and Scholia) |
|||
| (One intermediate revision by one other user not shown) | |||
| Line 6: | Line 6: | ||
** base, past and 3rd person present tense forms of verbs | ** base, past and 3rd person present tense forms of verbs | ||
* Originally proposed in [http://aclweb.org/anthology//N/N13/N13-1090.pdf Mikolov et al. (2013)] | * Originally proposed in [http://aclweb.org/anthology//N/N13/N13-1090.pdf Mikolov et al. (2013)] | ||
| + | * [https://www.wikidata.org/wiki/Q55387870 Wikidata] and [https://tools.wmflabs.org/scholia/use/Q55387870 Scholia] | ||
* see also: [[Similarity (State of the art)]] | * see also: [[Similarity (State of the art)]] | ||
| Line 49: | Line 50: | ||
[[Category:State of the art]] | [[Category:State of the art]] | ||
[[Category:Similarity]] | [[Category:Similarity]] | ||
| + | [[Category:Analogy]] | ||
Latest revision as of 06:23, 5 July 2018
- 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)
- Wikidata and Scholia
- 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).