mirror of https://github.com/explosion/spaCy.git
147 lines
3.6 KiB
JSON
147 lines
3.6 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-06/schema",
|
|
"title": "Training data for spaCy models",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"text": {
|
|
"title": "The text of the training example",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"ents": {
|
|
"title": "Named entity spans in the text",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"start": {
|
|
"title": "Start character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"end": {
|
|
"title": "End character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"label": {
|
|
"title": "Entity label",
|
|
"type": "string",
|
|
"minLength": 1,
|
|
"pattern": "^[A-Z0-9]*$"
|
|
}
|
|
},
|
|
"required": [
|
|
"start",
|
|
"end",
|
|
"label"
|
|
]
|
|
}
|
|
},
|
|
"sents": {
|
|
"title": "Sentence spans in the text",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"start": {
|
|
"title": "Start character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"end": {
|
|
"title": "End character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"required": [
|
|
"start",
|
|
"end"
|
|
]
|
|
}
|
|
},
|
|
"cats": {
|
|
"title": "Text categories for the text classifier",
|
|
"type": "object",
|
|
"patternProperties": {
|
|
"*": {
|
|
"title": "A text category",
|
|
"oneOf": [
|
|
{
|
|
"type": "boolean"
|
|
},
|
|
{
|
|
"type": "number",
|
|
"minimum": 0
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"propertyNames": {
|
|
"pattern": "^[A-Z0-9]*$",
|
|
"minLength": 1
|
|
}
|
|
},
|
|
"tokens": {
|
|
"title": "The tokens in the text",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"minProperties": 1,
|
|
"properties": {
|
|
"id": {
|
|
"title": "Token ID, usually token index",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"start": {
|
|
"title": "Start character offset of the token",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"end": {
|
|
"title": "End character offset of the token",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"pos": {
|
|
"title": "Coarse-grained part-of-speech tag",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"tag": {
|
|
"title": "Fine-grained part-of-speech tag",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"dep": {
|
|
"title": "Dependency label",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"head": {
|
|
"title": "Index of the token's head",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"required": [
|
|
"start",
|
|
"end"
|
|
]
|
|
}
|
|
},
|
|
"_": {
|
|
"title": "Custom user space",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"required": [
|
|
"text"
|
|
]
|
|
}
|
|
}
|