spaCy/website/docs/usage/101/_architecture.md
2020-08-10 23:41:09 +02:00

9.1 KiB

The central data structures in spaCy are the Language class, the Vocab and the Doc object. The Language class is used to process a text and turn it into a Doc object. It's typically stored as a variable called nlp. The Doc object owns the sequence of tokens and all their annotations. By centralizing strings, word vectors and lexical attributes in the Vocab, we avoid storing multiple copies of this data. This saves memory, and ensures there's a single source of truth.

Text annotations are also designed to allow a single source of truth: the Doc object owns the data, and Span and Token are views that point into it. The Doc object is constructed by the Tokenizer, and then modified in place by the components of the pipeline. The Language object coordinates these components. It takes raw text and sends it through the pipeline, returning an annotated document. It also orchestrates training and serialization.

Library architecture

Container objects

Name Description
Language Processing class that turns text into Doc objects. Different languages implement their own subclasses of it. The variable is typically called nlp.
Doc A container for accessing linguistic annotations.
Span A slice from a Doc object.
Token An individual token — i.e. a word, punctuation symbol, whitespace, etc.
Lexeme An entry in the vocabulary. It's a word type with no context, as opposed to a word token. It therefore has no part-of-speech tag, dependency parse etc.
Example A collection of training annotations, containing two Doc objects: the reference data and the predictions.
DocBin A collection of Doc objects for efficient binary serialization. Also used for training data.

Processing pipeline

The processing pipeline consists of one or more pipeline components that are called on the Doc in order. The tokenizer runs before the components. Pipeline components can be added using Language.add_pipe. They can contain a statistical model and trained weights, or only make rule-based modifications to the Doc. spaCy provides a range of built-in components for different language processing tasks and also allows adding custom components.

The processing pipeline

Name Description
Tokenizer Segment raw text and create Doc objects from the words.
Tok2Vec Apply a "token-to-vector" model and set its outputs.
Transformer Use a transformer model and set its outputs.
Lemmatizer Determine the base forms of words.
Morphologizer Predict morphological features and coarse-grained part-of-speech tags.
Tagger Predict part-of-speech tags.
AttributeRuler Set token attributes using matcher rules.
DependencyParser Predict syntactic dependencies.
EntityRecognizer Predict named entities, e.g. persons or products.
EntityRuler Add entity spans to the Doc using token-based rules or exact phrase matches.
EntityLinker Disambiguate named entities to nodes in a knowledge base.
TextCategorizer Predict categories or labels over the whole document.
Sentencizer Implement rule-based sentence boundary detection that doesn't require the dependency parse.
SentenceRecognizer Predict sentence boundaries.
Other functions Automatically apply something to the Doc, e.g. to merge spans of tokens.
Pipe Base class that all trainable pipeline components inherit from.

Matchers

Matchers help you find and extract information from Doc objects based on match patterns describing the sequences you're looking for. A matcher operates on a Doc and gives you access to the matched tokens in context.

Name Description
Matcher Match sequences of tokens, based on pattern rules, similar to regular expressions.
PhraseMatcher Match sequences of tokens based on phrases.
DependencyMatcher Match sequences of tokens based on dependency trees using the Semgrex syntax.

Other classes

Name Description
Vocab The shared vocabulary that stores strings and gives you access to Lexeme objects.
StringStore Map strings to and from hash values.
Vectors Container class for vector data keyed by string.
Lookups Container for convenient access to large lookup tables and dictionaries.
Morphology Assign linguistic features like lemmas, noun case, verb tense etc. based on the word and its part-of-speech tag.
MorphAnalysis A morphological analysis.
KnowledgeBase Storage for entities and aliases of a knowledge base for entity linking.
Scorer Compute evaluation scores.
Corpus Class for managing annotated corpora for training and evaluation data.