POS & DEP model for spaCy 2.3 based on SynTagRus and navec

POS & DEP model for spaCy 2.3: POS tagger and DEP (syntax analysis) models, trained on SynTagRus, using Navec vectors & pymorphy2 morphology.

Quality on SynTagRus-test:

POS | 95.31%
DEP UAS | 91.77%
DEP LAS | 89.12%

Accuracy.txt:

Itn  Tag Loss    Tag %    Dep Loss    UAS     LAS    NER Loss   NER P   NER R   NER F   Token %  CPU WPS  GPU WPS
---  ---------  --------  ---------  ------  ------  ---------  ------  ------  ------  -------  -------  -------
 30  24154.514    95.310  196988.805  91.777  89.124      0.000   0.000   0.000   0.000  100.000     6001    11902

How to use it: unpack into your project root folder, then

import ru2_syntagrus
ru2_syntagrus.load_ru2('path_to/ru2_syntagrus')

Or you could just use spacy.load('path_to/ru2_syntagrus/') but then lemmas will be a bit worse.

License: CC BY-NC-SA 4.0 (same as SynTagRus)
This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
http://creativecommons.org/licenses/by-nc-sa/4.0/