| { | |
| "algorithm": { | |
| "command": null, | |
| "id": 0, | |
| "name": "Gensim Continuous Skipgram", | |
| "tool": "Gensim", | |
| "url": "https://github.com/RaRe-Technologies/gensim", | |
| "version": "3.6" | |
| }, | |
| "contents": [ | |
| { | |
| "filename": "model.txt", | |
| "format": "text" | |
| }, | |
| { | |
| "filename": "model.bin", | |
| "format": "data" | |
| }, | |
| { | |
| "filename": "meta.json", | |
| "format": "json" | |
| } | |
| ], | |
| "corpus": [ | |
| { | |
| "NER": true, | |
| "case preserved": false, | |
| "description": "Russian National Corpus", | |
| "id": 88, | |
| "language": "rus", | |
| "lemmatized": true, | |
| "public": false, | |
| "stop words removal": null, | |
| "tagger": "UDPipe 1.2", | |
| "tagset": "UPoS", | |
| "tokens": 270000000, | |
| "url": "http://ruscorpora.ru/" | |
| }, | |
| { | |
| "NER": true, | |
| "case preserved": false, | |
| "description": "Russian Wikipedia dump of December 2018", | |
| "id": 91, | |
| "language": "rus", | |
| "lemmatized": true, | |
| "public": true, | |
| "stop words removal": null, | |
| "tagger": "UDPipe 1.2", | |
| "tagset": "UPoS", | |
| "tokens": 518531000, | |
| "tool": "https://github.com/RaRe-Technologies/gensim/blob/master/gensim/scripts/segment_wiki.py", | |
| "url": "https://dumps.wikimedia.org/" | |
| } | |
| ], | |
| "creators": [ | |
| { | |
| "email": "andreku@ifi.uio.no", | |
| "name": "Andrey Kutuzov" | |
| } | |
| ], | |
| "dimensions": 300, | |
| "documentation": [ | |
| "https://rusvectores.org" | |
| ], | |
| "external_id": "ruwikiruscorpora-func_upos_skipgram_300_5_2019", | |
| "handle": "http://vectors.nlpl.eu/repository/20/183.zip", | |
| "id": 183, | |
| "iterations": 10, | |
| "vocabulary size": 248118, | |
| "window": 5 | |
| } |