File size: 1,746 Bytes
1801925 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
{
"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": "meta.json",
"format": "json"
}
],
"corpus": [
{
"NER": false,
"case preserved": true,
"description": "English Wikipedia Dump of February 2017",
"id": 0,
"language": "eng",
"lemmatized": true,
"public": true,
"stop words removal": "NLTK",
"tagger": "Stanford Core NLP v. 3.6.0",
"tagset": null,
"tokens": 2252637050,
"tool": "Wikipedia Extractor",
"url": "https://dumps.wikimedia.org/"
},
{
"NER": false,
"case preserved": true,
"description": "Gigaword 5th Edition",
"id": 3,
"language": "eng",
"lemmatized": true,
"public": false,
"stop words removal": "NLTK",
"tagger": "Stanford Core NLP v. 3.6.0",
"tagset": null,
"tokens": 4815382730,
"tool": null,
"url": "https://catalog.ldc.upenn.edu/LDC2011T07"
}
],
"creators": [
{
"email": "andreku@ifi.uio.no",
"name": "Andrey Kutuzov"
}
],
"dimensions": 300,
"handle": "http://vectors.nlpl.eu/repository/20/17.zip",
"id": 17,
"iterations": 5,
"vocabulary size": 259882,
"window": 5
} |