spaCy/website/api/_data.json

{
    "sidebar": {
        "Overview": {
            "Architecture": "./",
            "Annotation Specs": "annotation",
            "Functions": "top-level"
        },
        "Containers": {
            "Doc": "doc",
            "Token": "token",
            "Span": "span",
            "Lexeme": "lexeme"
        },

        "Pipeline": {
            "Language": "language",
            "Pipe": "pipe",
            "Tensorizer": "tensorizer",
            "Tagger": "tagger",
            "DependencyParser": "dependencyparser",
            "EntityRecognizer": "entityrecognizer",
            "TextCategorizer": "textcategorizer",
            "Tokenizer": "tokenizer",
            "Lemmatizer": "lemmatizer",
            "Matcher": "matcher",
            "PhraseMatcher": "phrasematcher"
        },

        "Other": {
            "Vocab": "vocab",
            "StringStore": "stringstore",
            "Vectors": "vectors",
            "GoldParse": "goldparse",
            "GoldCorpus": "goldcorpus"
        }
    },

    "index": {
        "title": "Architecture",
        "next": "annotation",
        "menu": {
            "Basics": "basics",
            "Neural Network Model": "nn-model",
            "Cython Conventions": "cython"
        }
    },

    "top-level": {
        "title": "Top-level Functions",
        "menu": {
            "spacy": "spacy",
            "displacy": "displacy",
            "Utility Functions": "util",
            "Compatibility": "compat",
            "Command Line": "cli"
        }
    },

    "language": {
        "title": "Language",
        "tag": "class",
        "teaser": "A text-processing pipeline.",
        "source": "spacy/language.py"
    },

    "doc": {
        "title": "Doc",
        "tag": "class",
        "teaser": "A container for accessing linguistic annotations.",
        "source": "spacy/tokens/doc.pyx"
    },

    "token": {
        "title": "Token",
        "tag": "class",
        "source": "spacy/tokens/token.pyx"
    },

    "span": {
        "title": "Span",
        "tag": "class",
        "source": "spacy/tokens/span.pyx"
    },

    "lexeme": {
        "title": "Lexeme",
        "tag": "class",
        "source": "spacy/lexeme.pyx"
    },

    "vocab": {
        "title": "Vocab",
        "teaser": "A storage class for vocabulary and other data shared across a language.",
        "tag": "class",
        "source": "spacy/vocab.pyx"
    },

    "stringstore": {
        "title": "StringStore",
        "tag": "class",
        "source": "spacy/strings.pyx"
    },

    "matcher": {
        "title": "Matcher",
        "teaser": "Match sequences of tokens, based on pattern rules.",
        "tag": "class",
        "source": "spacy/matcher.pyx"
    },

    "phrasematcher": {
        "title": "PhraseMatcher",
        "teaser": "Match sequences of tokens, based on documents.",
        "tag": "class",
        "tag_new": 2,
        "source": "spacy/matcher.pyx"
    },

    "pipe": {
        "title": "Pipe",
        "teaser": "Abstract base class defining the API for pipeline components.",
        "tag": "class",
        "tag_new": 2,
        "source": "spacy/pipeline.pyx"
    },

    "dependenyparser": {
        "title": "DependencyParser",
        "tag": "class",
        "source": "spacy/pipeline.pyx"
    },

    "entityrecognizer": {
        "title": "EntityRecognizer",
        "teaser": "Annotate named entities on documents.",
        "tag": "class",
        "source": "spacy/pipeline.pyx"
    },

    "textcategorizer": {
        "title": "TextCategorizer",
        "teaser": "Add text categorization models to spaCy pipelines.",
        "tag": "class",
        "tag_new": 2,
        "source": "spacy/pipeline.pyx"
    },

    "dependencyparser": {
        "title": "DependencyParser",
        "teaser": "Annotate syntactic dependencies on documents.",
        "tag": "class",
        "source": "spacy/pipeline.pyx"
    },

    "tokenizer": {
        "title": "Tokenizer",
        "teaser": "Segment text into words, punctuations marks etc.",
        "tag": "class",
        "source": "spacy/tokenizer.pyx"
    },

    "lemmatizer": {
        "title": "Lemmatizer",
        "teaser": "Assign the base forms of words.",
        "tag": "class",
        "source": "spacy/lemmatizer.py"
    },

    "tagger": {
        "title": "Tagger",
        "teaser": "Annotate part-of-speech tags on documents.",
        "tag": "class",
        "source": "spacy/pipeline.pyx"
    },

    "tensorizer": {
        "title": "Tensorizer",
        "teaser": "Add a tensor with position-sensitive meaning representations to a document.",
        "tag": "class",
        "tag_new": 2,
        "source": "spacy/pipeline.pyx"
    },

    "goldparse": {
        "title": "GoldParse",
        "tag": "class",
        "source": "spacy/gold.pyx"
    },

    "goldcorpus": {
        "title": "GoldCorpus",
        "teaser": "An annotated corpus, using the JSON file format.",
        "tag": "class",
        "tag_new": 2,
        "source": "spacy/gold.pyx"
    },

    "vectors": {
        "title": "Vectors",
        "teaser": "Store, save and load word vectors.",
        "tag": "class",
        "tag_new": 2,
        "source": "spacy/vectors.pyx"
    },

    "annotation": {
        "title": "Annotation Specifications",
        "teaser": "Schemes used for labels, tags and training data.",
        "menu": {
            "Tokenization": "tokenization",
            "Sentence Boundaries": "sbd",
            "POS Tagging": "pos-tagging",
            "Lemmatization": "lemmatization",
            "Dependencies": "dependency-parsing",
            "Named Entities": "named-entities",
            "Training Data": "training"
        }
    }
}