explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity
master
spaCy/extra/example_data/training-data.json

642 lines
17 KiB
JSON
Raw Permalink Normal View History

Add training data JSON example
2017-10-24 13:05:10 +03:00
[
Use better training data JSON example
2017-10-24 16:35:16 +03:00
{
Update Example input JSON file to adhere to specification. (#3243) * Example file does not adhere to json input spec. According to the [json input spec ](https://spacy.io/api/annotation#json-input) the `id ` needs to be an `int` not a string. Using a string as `id` results in a `TypeError` when calling `spacy.gold.read_json_file()`. * Add spaCy Contributor Agreement.
2019-02-07 18:18:01 +03:00
"id": 42,
Use better training data JSON example
2017-10-24 16:35:16 +03:00
"paragraphs": [
{
"raw": "In an Oct. 19 review of \"The Misanthrope\" at Chicago's Goodman Theatre (\"Revitalized Classics Take the Stage in Windy City,\" Leisure & Arts), the role of Celimene, played by Kim Cattrall, was mistakenly attributed to Christina Haag. Ms. Haag plays Elianti.",
"sentences": [
{
"tokens": [
{
Revert training example edit from #4327 (#4403) I think the original annotation was correct and this change also unfortunately introduced a cycle into the dependency tree.
2019-10-10 18:00:26 +03:00
"head": 44,
Use better training data JSON example
2017-10-24 16:35:16 +03:00
"dep": "prep",
"tag": "IN",
"orth": "In",
"ner": "O",
"id": 0
},
{
"head": 3,
"dep": "det",
"tag": "DT",
"orth": "an",
"ner": "O",
"id": 1
},
{
"head": 2,
"dep": "nmod",
"tag": "NNP",
"orth": "Oct.",
"ner": "B-DATE",
"id": 2
},
{
"head": -1,
"dep": "nummod",
"tag": "CD",
"orth": "19",
"ner": "L-DATE",
"id": 3
},
{
"head": -4,
"dep": "pobj",
"tag": "NN",
"orth": "review",
"ner": "O",
"id": 4
},
{
"head": -1,
"dep": "prep",
"tag": "IN",
"orth": "of",
"ner": "O",
"id": 5
},
{
"head": 2,
"dep": "punct",
"tag": "``",
"orth": "``",
"ner": "O",
"id": 6
},
{
"head": 1,
"dep": "det",
"tag": "DT",
"orth": "The",
"ner": "B-WORK_OF_ART",
"id": 7
},
{
"head": -3,
"dep": "pobj",
"tag": "NN",
"orth": "Misanthrope",
"ner": "L-WORK_OF_ART",
"id": 8
},
{
"head": -1,
"dep": "punct",
"tag": "''",
"orth": "''",
"ner": "O",
"id": 9
},
{
"head": -2,
"dep": "prep",
"tag": "IN",
"orth": "at",
"ner": "O",
"id": 10
},
{
"head": 3,
"dep": "poss",
"tag": "NNP",
"orth": "Chicago",
"ner": "U-GPE",
"id": 11
},
{
"head": -1,
"dep": "case",
"tag": "POS",
"orth": "'s",
"ner": "O",
"id": 12
},
{
"head": 1,
"dep": "compound",
"tag": "NNP",
"orth": "Goodman",
"ner": "B-FAC",
"id": 13
},
{
"head": -4,
"dep": "pobj",
"tag": "NNP",
"orth": "Theatre",
"ner": "L-FAC",
"id": 14
},
{
"head": 4,
"dep": "punct",
"tag": "-LRB-",
"orth": "(",
"ner": "O",
"id": 15
},
{
"head": 3,
"dep": "punct",
"tag": "``",
"orth": "``",
"ner": "O",
"id": 16
},
{
"head": 1,
"dep": "amod",
"tag": "VBN",
"orth": "Revitalized",
"ner": "B-WORK_OF_ART",
"id": 17
},
{
"head": 1,
"dep": "nsubj",
"tag": "NNS",
"orth": "Classics",
"ner": "I-WORK_OF_ART",
"id": 18
},
{
"head": -15,
"dep": "appos",
"tag": "VBP",
"orth": "Take",
"ner": "I-WORK_OF_ART",
"id": 19
},
{
"head": 1,
"dep": "det",
"tag": "DT",
"orth": "the",
"ner": "I-WORK_OF_ART",
"id": 20
},
{
"head": -2,
"dep": "dobj",
"tag": "NN",
"orth": "Stage",
"ner": "I-WORK_OF_ART",
"id": 21
},
{
"head": -3,
"dep": "prep",
"tag": "IN",
"orth": "in",
"ner": "I-WORK_OF_ART",
"id": 22
},
{
"head": 1,
"dep": "compound",
"tag": "NNP",
"orth": "Windy",
"ner": "I-WORK_OF_ART",
"id": 23
},
{
"head": -2,
"dep": "pobj",
"tag": "NNP",
"orth": "City",
"ner": "L-WORK_OF_ART",
"id": 24
},
{
"head": -6,
"dep": "punct",
"tag": ",",
"orth": ",",
"ner": "O",
"id": 25
},
{
"head": -7,
"dep": "punct",
"tag": "''",
"orth": "''",
"ner": "O",
"id": 26
},
{
"head": -8,
"dep": "npadvmod",
"tag": "NN",
"orth": "Leisure",
"ner": "B-ORG",
"id": 27
},
{
"head": -1,
"dep": "cc",
"tag": "CC",
"orth": "&",
"ner": "I-ORG",
"id": 28
},
{
"head": -2,
"dep": "conj",
"tag": "NNS",
"orth": "Arts",
"ner": "L-ORG",
"id": 29
},
{
"head": -11,
"dep": "punct",
"tag": "-RRB-",
"orth": ")",
"ner": "O",
"id": 30
},
{
"head": 13,
"dep": "punct",
"tag": ",",
"orth": ",",
"ner": "O",
"id": 31
},
{
"head": 1,
"dep": "det",
"tag": "DT",
"orth": "the",
"ner": "O",
"id": 32
},
{
"head": 11,
"dep": "nsubjpass",
"tag": "NN",
"orth": "role",
"ner": "O",
"id": 33
},
{
"head": -1,
"dep": "prep",
"tag": "IN",
"orth": "of",
"ner": "O",
"id": 34
},
{
"head": -1,
"dep": "pobj",
"tag": "NNP",
"orth": "Celimene",
"ner": "U-PERSON",
"id": 35
},
{
"head": -3,
"dep": "punct",
"tag": ",",
"orth": ",",
"ner": "O",
"id": 36
},
{
"head": -4,
"dep": "acl",
"tag": "VBN",
"orth": "played",
"ner": "O",
"id": 37
},
{
"head": -1,
"dep": "agent",
"tag": "IN",
"orth": "by",
"ner": "O",
"id": 38
},
{
"head": 1,
"dep": "compound",
"tag": "NNP",
"orth": "Kim",
"ner": "B-PERSON",
"id": 39
},
{
"head": -2,
"dep": "pobj",
"tag": "NNP",
"orth": "Cattrall",
"ner": "L-PERSON",
"id": 40
},
{
"head": -8,
"dep": "punct",
"tag": ",",
"orth": ",",
"ner": "O",
"id": 41
},
{
"head": 2,
"dep": "auxpass",
"tag": "VBD",
"orth": "was",
"ner": "O",
"id": 42
},
{
"head": 1,
"dep": "advmod",
"tag": "RB",
"orth": "mistakenly",
"ner": "O",
"id": 43
},
{
"head": 0,
"dep": "root",
"tag": "VBN",
"orth": "attributed",
"ner": "O",
"id": 44
},
{
"head": -1,
"dep": "prep",
"tag": "IN",
"orth": "to",
"ner": "O",
"id": 45
},
{
"head": 1,
"dep": "compound",
"tag": "NNP",
"orth": "Christina",
"ner": "B-PERSON",
"id": 46
},
{
"head": -2,
"dep": "pobj",
"tag": "NNP",
"orth": "Haag",
"ner": "L-PERSON",
"id": 47
},
{
"head": -4,
"dep": "punct",
"tag": ".",
"orth": ".",
"ner": "O",
"id": 48
}
],
"brackets": [
{
"first": 2,
"last": 3,
"label": "NML"
},
{
"first": 1,
"last": 4,
"label": "NP"
},
{
"first": 7,
"last": 8,
"label": "NP-TTL"
},
{
"first": 11,
"last": 12,
"label": "NP"
},
{
"first": 11,
"last": 14,
"label": "NP"
},
{
"first": 10,
"last": 14,
"label": "PP-LOC"
},
{
"first": 6,
"last": 14,
"label": "NP"
},
{
"first": 5,
"last": 14,
"label": "PP"
},
{
"first": 1,
"last": 14,
"label": "NP"
},
{
"first": 17,
"last": 18,
"label": "NP-SBJ"
},
{
"first": 20,
"last": 21,
"label": "NP"
},
{
"first": 23,
"last": 24,
"label": "NP"
},
{
"first": 22,
"last": 24,
"label": "PP-LOC"
},
{
"first": 19,
"last": 24,
"label": "VP"
},
{
"first": 17,
"last": 24,
"label": "S-HLN"
},
{
"first": 27,
"last": 29,
"label": "NP-TMP"
},
{
"first": 15,
"last": 30,
"label": "NP"
},
{
"first": 1,
"last": 30,
"label": "NP"
},
{
"first": 0,
"last": 30,
"label": "PP-LOC"
},
{
"first": 32,
"last": 33,
"label": "NP"
},
{
"first": 35,
"last": 35,
"label": "NP"
},
{
"first": 34,
"last": 35,
"label": "PP"
},
{
"first": 32,
"last": 35,
"label": "NP"
},
{
"first": 39,
"last": 40,
"label": "NP-LGS"
},
{
"first": 38,
"last": 40,
"label": "PP"
},
{
"first": 37,
"last": 40,
"label": "VP"
},
{
"first": 32,
"last": 41,
"label": "NP-SBJ-2"
},
{
"first": 43,
"last": 43,
"label": "ADVP-MNR"
},
{
"first": 46,
"last": 47,
"label": "NP"
},
{
"first": 45,
"last": 47,
"label": "PP-CLR"
},
{
"first": 44,
"last": 47,
"label": "VP"
},
{
"first": 42,
"last": 47,
"label": "VP"
},
{
"first": 0,
"last": 48,
"label": "S"
}
]
},
{
"tokens": [
{
"head": 1,
"dep": "compound",
"tag": "NNP",
"orth": "Ms.",
"ner": "O",
"id": 0
},
{
"head": 1,
"dep": "nsubj",
"tag": "NNP",
"orth": "Haag",
"ner": "U-PERSON",
"id": 1
},
{
"head": 0,
"dep": "root",
"tag": "VBZ",
"orth": "plays",
"ner": "O",
"id": 2
},
{
"head": -1,
"dep": "dobj",
"tag": "NNP",
"orth": "Elianti",
"ner": "U-PERSON",
"id": 3
},
{
"head": -2,
"dep": "punct",
"tag": ".",
"orth": ".",
"ner": "O",
"id": 4
}
],
"brackets": [
{
"first": 0,
"last": 1,
"label": "NP-SBJ"
},
{
"first": 3,
"last": 3,
"label": "NP"
},
{
"first": 2,
"last": 3,
"label": "VP"
},
{
"first": 0,
"last": 4,
"label": "S"
}
]
}
]
}
]
}
]
Reference in New Issue Copy Permalink