Get started

spaCy 101: Everything you need to know

The most important concepts, explained in simple terms

Whether you’re new to spaCy, or just want to brush up on some NLP basics and implementation details – this page should have you covered. Each section will explain one of spaCy’s features in simple terms and with examples or illustrations. Some sections will also reappear across the usage guides as a quick introduction.

What’s spaCy?

spaCy is a free, open-source library for advanced Natural Language Processing (NLP) in Python.

If you’re working with a lot of text, you’ll eventually want to know more about it. For example, what’s it about? What do the words mean in context? Who is doing what to whom? What companies and products are mentioned? Which texts are similar to each other?

spaCy is designed specifically for production use and helps you build applications that process and “understand” large volumes of text. It can be used to build information extraction or natural language understanding systems, or to pre-process text for deep learning.

What spaCy isn’t

  • spaCy is not a platform or “an API”. Unlike a platform, spaCy does not provide a software as a service, or a web application. It’s an open-source library designed to help you build NLP applications, not a consumable service.
  • spaCy is not an out-of-the-box chat bot engine. While spaCy can be used to power conversational applications, it’s not designed specifically for chat bots, and only provides the underlying text processing capabilities.
  • spaCy is not research software. It’s built on the latest research, but it’s designed to get things done. This leads to fairly different design decisions than NLTK or CoreNLP, which were created as platforms for teaching and research. The main difference is that spaCy is integrated and opinionated. spaCy tries to avoid asking the user to choose between multiple algorithms that deliver equivalent functionality. Keeping the menu small lets spaCy deliver generally better performance and developer experience.
  • spaCy is not a company. It’s an open-source library. Our company publishing spaCy and other software is called Explosion.


In the documentation, you’ll come across mentions of spaCy’s features and capabilities. Some of them refer to linguistic concepts, while others are related to more general machine learning functionality.

TokenizationSegmenting text into words, punctuations marks etc.
Part-of-speech (POS) TaggingAssigning word types to tokens, like verb or noun.
Dependency ParsingAssigning syntactic dependency labels, describing the relations between individual tokens, like subject or object.
LemmatizationAssigning the base forms of words. For example, the lemma of “was” is “be”, and the lemma of “rats” is “rat”.
Sentence Boundary Detection (SBD)Finding and segmenting individual sentences.
Named Entity Recognition (NER)Labelling named “real-world” objects, like persons, companies or locations.
Entity Linking (EL)Disambiguating textual entities to unique identifiers in a knowledge base.
SimilarityComparing words, text spans and documents and how similar they are to each other.
Text ClassificationAssigning categories or labels to a whole document, or parts of a document.
Rule-based MatchingFinding sequences of tokens based on their texts and linguistic annotations, similar to regular expressions.
TrainingUpdating and improving a statistical model’s predictions.
SerializationSaving objects to files or byte strings.

Statistical models

While some of spaCy’s features work independently, others require trained pipelines to be loaded, which enable spaCy to predict linguistic annotations – for example, whether a word is a verb or a noun. A trained pipeline can consist of multiple components that use a statistical model trained on labeled data. spaCy currently offers trained pipelines for a variety of languages, which can be installed as individual Python modules. Pipeline packages can differ in size, speed, memory usage, accuracy and the data they include. The package you choose always depends on your use case and the texts you’re working with. For a general-purpose use case, the small, default packages are always a good start. They typically include the following components:

  • Binary weights for the part-of-speech tagger, dependency parser and named entity recognizer to predict those annotations in context.
  • Lexical entries in the vocabulary, i.e. words and their context-independent attributes like the shape or spelling.
  • Data files like lemmatization rules and lookup tables.
  • Word vectors, i.e. multi-dimensional meaning representations of words that let you determine how similar they are to each other.
  • Configuration options, like the language and processing pipeline settings and model implementations to use, to put spaCy in the correct state when you load the pipeline.

Linguistic annotations

spaCy provides a variety of linguistic annotations to give you insights into a text’s grammatical structure. This includes the word types, like the parts of speech, and how the words are related to each other. For example, if you’re analyzing text, it makes a huge difference whether a noun is the subject of a sentence, or the object – or whether “google” is used as a verb, or refers to the website or company in a specific context.

Once you’ve downloaded and installed a trained pipeline, you can load it via spacy.load. This will return a Language object containing all components and data needed to process text. We usually call it nlp. Calling the nlp object on a string of text will return a processed Doc:

Editable CodespaCy v3.7 · Python 3 · via Binder

Even though a Doc is processed – e.g. split into individual words and annotated – it still holds all information of the original text, like whitespace characters. You can always get the offset of a token into the original string, or reconstruct the original by joining the tokens and their trailing whitespace. This way, you’ll never lose any information when processing text with spaCy.


During processing, spaCy first tokenizes the text, i.e. segments it into words, punctuation and so on. This is done by applying rules specific to each language. For example, punctuation at the end of a sentence should be split off – whereas “U.K.” should remain one token. Each Doc consists of individual tokens, and we can iterate over them:

Editable CodespaCy v3.7 · Python 3 · via Binder


First, the raw text is split on whitespace characters, similar to text.split(' '). Then, the tokenizer processes the text from left to right. On each substring, it performs two checks:

  1. Does the substring match a tokenizer exception rule? For example, “don’t” does not contain whitespace, but should be split into two tokens, “do” and “n’t”, while “U.K.” should always remain one token.

  2. Can a prefix, suffix or infix be split off? For example punctuation like commas, periods, hyphens or quotes.

If there’s a match, the rule is applied and the tokenizer continues its loop, starting with the newly split substrings. This way, spaCy can split complex, nested tokens like combinations of abbreviations and multiple punctuation marks.

Example of the tokenization process

While punctuation rules are usually pretty general, tokenizer exceptions strongly depend on the specifics of the individual language. This is why each available language has its own subclass, like English or German, that loads in lists of hard-coded data and exception rules.

Part-of-speech tags and dependencies Needs model

After tokenization, spaCy can parse and tag a given Doc. This is where the trained pipeline and its statistical models come in, which enable spaCy to make predictions of which tag or label most likely applies in this context. A trained component includes binary data that is produced by showing a system enough examples for it to make predictions that generalize across the language – for example, a word following “the” in English is most likely a noun.

Linguistic annotations are available as Token attributes. Like many NLP libraries, spaCy encodes all strings to hash values to reduce memory usage and improve efficiency. So to get the readable string representation of an attribute, we need to add an underscore _ to its name:

Editable CodespaCy v3.7 · Python 3 · via Binder


Using spaCy’s built-in displaCy visualizer, here’s what our example sentence and its dependencies look like:

Named Entities Needs model

A named entity is a “real-world object” that’s assigned a name – for example, a person, a country, a product or a book title. spaCy can recognize various types of named entities in a document, by asking the model for a prediction. Because models are statistical and strongly depend on the examples they were trained on, this doesn’t always work perfectly and might need some tuning later, depending on your use case.

Named entities are available as the ents property of a Doc:

Editable CodespaCy v3.7 · Python 3 · via Binder

Apple05ORGCompanies, agencies, institutions.
U.K.2731GPEGeopolitical entity, i.e. countries, cities, states.
$1 billion4454MONEYMonetary values, including unit.

Using spaCy’s built-in displaCy visualizer, here’s what our example sentence and its named entities look like:

Apple ORG is looking at buying U.K. GPE startup for $1 billion MONEY

Word vectors and similarity Needs model

Similarity is determined by comparing word vectors or “word embeddings”, multi-dimensional meaning representations of a word. Word vectors can be generated using an algorithm like word2vec and usually look like this:


Pipeline packages that come with built-in word vectors make them available as the Token.vector attribute. Doc.vector and Span.vector will default to an average of their token vectors. You can also check if a token has a vector assigned, and get the L2 norm, which can be used to normalize vectors.

Editable CodespaCy v3.7 · Python 3 · via Binder

The words “dog”, “cat” and “banana” are all pretty common in English, so they’re part of the pipeline’s vocabulary, and come with a vector. The word “afskfsd” on the other hand is a lot less common and out-of-vocabulary – so its vector representation consists of 300 dimensions of 0, which means it’s practically nonexistent. If your application will benefit from a large vocabulary with more vectors, you should consider using one of the larger pipeline packages or loading in a full vector package, for example, en_core_web_lg, which includes 685k unique vectors.

spaCy is able to compare two objects, and make a prediction of how similar they are. Predicting similarity is useful for building recommendation systems or flagging duplicates. For example, you can suggest a user content that’s similar to what they’re currently looking at, or label a support ticket as a duplicate if it’s very similar to an already existing one.

Each Doc, Span, Token and Lexeme comes with a .similarity method that lets you compare it with another object, and determine the similarity. Of course similarity is always subjective – whether two words, spans or documents are similar really depends on how you’re looking at it. spaCy’s similarity implementation usually assumes a pretty general-purpose definition of similarity.

Editable CodespaCy v3.7 · Python 3 · via Binder

What to expect from similarity results

Computing similarity scores can be helpful in many situations, but it’s also important to maintain realistic expectations about what information it can provide. Words can be related to each other in many ways, so a single “similarity” score will always be a mix of different signals, and vectors trained on different data can produce very different results that may not be useful for your purpose. Here are some important considerations to keep in mind:

  • There’s no objective definition of similarity. Whether “I like burgers” and “I like pasta” is similar depends on your application. Both talk about food preferences, which makes them very similar – but if you’re analyzing mentions of food, those sentences are pretty dissimilar, because they talk about very different foods.
  • The similarity of Doc and Span objects defaults to the average of the token vectors. This means that the vector for “fast food” is the average of the vectors for “fast” and “food”, which isn’t necessarily representative of the phrase “fast food”.
  • Vector averaging means that the vector of multiple tokens is insensitive to the order of the words. Two documents expressing the same meaning with dissimilar wording will return a lower similarity score than two documents that happen to contain the same words while expressing different meanings.


When you call nlp on a text, spaCy first tokenizes the text to produce a Doc object. The Doc is then processed in several different steps – this is also referred to as the processing pipeline. The pipeline used by the trained pipelines typically include a tagger, a lemmatizer, a parser and an entity recognizer. Each pipeline component returns the processed Doc, which is then passed on to the next component.

The processing pipeline
tokenizerTokenizerDocSegment text into tokens.
processing pipeline
taggerTaggerToken.tagAssign part-of-speech tags.
parserDependencyParserToken.head, Token.dep, Doc.sents, Doc.noun_chunksAssign dependency labels.
nerEntityRecognizerDoc.ents, Token.ent_iob, Token.ent_typeDetect and label named entities.
lemmatizerLemmatizerToken.lemmaAssign base forms.
textcatTextCategorizerDoc.catsAssign document labels.
customcustom,, Span._.xxxAssign custom attributes, methods or properties.

The capabilities of a processing pipeline always depend on the components, their models and how they were trained. For example, a pipeline for named entity recognition needs to include a trained named entity recognizer component with a statistical model and weights that enable it to make predictions of entity labels. This is why each pipeline specifies its components and their settings in the config:

The statistical components like the tagger or parser are typically independent and don’t share any data between each other. For example, the named entity recognizer doesn’t use any features set by the tagger and parser, and so on. This means that you can swap them, or remove single components from the pipeline without affecting the others. However, components may share a “token-to-vector” component like Tok2Vec or Transformer. You can read more about this in the docs on embedding layers.

Custom components may also depend on annotations set by other components. For example, a custom lemmatizer may need the part-of-speech tags assigned, so it’ll only work if it’s added after the tagger. The parser will respect pre-defined sentence boundaries, so if a previous component in the pipeline sets them, its dependency predictions may be different. Similarly, it matters if you add the EntityRuler before or after the statistical entity recognizer: if it’s added before, the entity recognizer will take the existing entities into account when making predictions. The EntityLinker, which resolves named entities to knowledge base IDs, should be preceded by a pipeline component that recognizes entities such as the EntityRecognizer.

The tokenizer is a “special” component and isn’t part of the regular pipeline. It also doesn’t show up in nlp.pipe_names. The reason is that there can only really be one tokenizer, and while all other pipeline components take a Doc and return it, the tokenizer takes a string of text and turns it into a Doc. You can still customize the tokenizer, though. nlp.tokenizer is writable, so you can either create your own Tokenizer class from scratch, or even replace it with an entirely custom function.


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 {w:1080, h:1254}

Container objects

DocA container for accessing linguistic annotations.
DocBinA collection of Doc objects for efficient binary serialization. Also used for training data.
ExampleA collection of training annotations, containing two Doc objects: the reference data and the predictions.
LanguageProcessing class that turns text into Doc objects. Different languages implement their own subclasses of it. The variable is typically called nlp.
LexemeAn 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.
SpanA slice from a Doc object.
SpanGroupA named collection of spans belonging to a Doc.
TokenAn individual token — i.e. a word, punctuation symbol, whitespace, etc.

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
AttributeRulerSet token attributes using matcher rules.
DependencyParserPredict syntactic dependencies.
EditTreeLemmatizerPredict base forms of words.
EntityLinkerDisambiguate named entities to nodes in a knowledge base.
EntityRecognizerPredict named entities, e.g. persons or products.
EntityRulerAdd entity spans to the Doc using token-based rules or exact phrase matches.
LemmatizerDetermine the base forms of words using rules and lookups.
MorphologizerPredict morphological features and coarse-grained part-of-speech tags.
SentenceRecognizerPredict sentence boundaries.
SentencizerImplement rule-based sentence boundary detection that doesn’t require the dependency parse.
TaggerPredict part-of-speech tags.
TextCategorizerPredict categories or labels over the whole document.
Tok2VecApply a “token-to-vector” model and set its outputs.
TokenizerSegment raw text and create Doc objects from the words.
TrainablePipeClass that all trainable pipeline components inherit from.
TransformerUse a transformer model and set its outputs.
Other functionsAutomatically apply something to the Doc, e.g. to merge spans of tokens.


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.

DependencyMatcherMatch sequences of tokens based on dependency trees using Semgrex operators.
MatcherMatch sequences of tokens, based on pattern rules, similar to regular expressions.
PhraseMatcherMatch sequences of tokens based on phrases.

Other classes

CorpusClass for managing annotated corpora for training and evaluation data.
KnowledgeBaseAbstract base class for storage and retrieval of data for entity linking.
InMemoryLookupKBImplementation of KnowledgeBase storing all data in memory.
CandidateObject associating a textual mention with a specific entity contained in a KnowledgeBase.
LookupsContainer for convenient access to large lookup tables and dictionaries.
MorphAnalysisA morphological analysis.
MorphologyStore morphological analyses and map them to and from hash values.
ScorerCompute evaluation scores.
StringStoreMap strings to and from hash values.
VectorsContainer class for vector data keyed by string.
VocabThe shared vocabulary that stores strings and gives you access to Lexeme objects.

Vocab, hashes and lexemes

Whenever possible, spaCy tries to store data in a vocabulary, the Vocab, that will be shared by multiple documents. To save memory, spaCy also encodes all strings to hash values – in this case for example, “coffee” has the hash 3197928453018144401. Entity labels like “ORG” and part-of-speech tags like “VERB” are also encoded. Internally, spaCy only “speaks” in hash values.

Doc, Vocab, Lexeme and StringStore

If you process lots of documents containing the word “coffee” in all kinds of different contexts, storing the exact string “coffee” every time would take up way too much space. So instead, spaCy hashes the string and stores it in the StringStore. You can think of the StringStore as a lookup table that works in both directions – you can look up a string to get its hash, or a hash to get its string:

Editable CodespaCy v3.7 · Python 3 · via Binder

Now that all strings are encoded, the entries in the vocabulary don’t need to include the word text themselves. Instead, they can look it up in the StringStore via its hash value. Each entry in the vocabulary, also called Lexeme, contains the context-independent information about a word. For example, no matter if “love” is used as a verb or a noun in some context, its spelling and whether it consists of alphabetic characters won’t ever change. Its hash value will also always be the same.

Editable CodespaCy v3.7 · Python 3 · via Binder


The mapping of words to hashes doesn’t depend on any state. To make sure each value is unique, spaCy uses a hash function to calculate the hash based on the word string. This also means that the hash for “coffee” will always be the same, no matter which pipeline you’re using or how you’ve configured spaCy.

However, hashes cannot be reversed and there’s no way to resolve 3197928453018144401 back to “coffee”. All spaCy can do is look it up in the vocabulary. That’s why you always need to make sure all objects you create have access to the same vocabulary. If they don’t, spaCy might not be able to find the strings it needs.

Editable CodespaCy v3.7 · Python 3 · via Binder

If the vocabulary doesn’t contain a string for 3197928453018144401, spaCy will raise an error. You can re-add “coffee” manually, but this only works if you actually know that the document contains that word. To prevent this problem, spaCy will also export the Vocab when you save a Doc or nlp object. This will give you the object and its encoded annotations, plus the “key” to decode it.


If you’ve been modifying the pipeline, vocabulary, vectors and entities, or made updates to the component models, you’ll eventually want to save your progress – for example, everything that’s in your nlp object. This means you’ll have to translate its contents and structure into a format that can be saved, like a file or a byte string. This process is called serialization. spaCy comes with built-in serialization methods and supports the Pickle protocol.

All container classes, i.e. Language (nlp), Doc, Vocab and StringStore have the following methods available:

to_bytesbytesdata = nlp.to_bytes()


spaCy’s tagger, parser, text categorizer and many other components are powered by statistical models. Every “decision” these components make – for example, which part-of-speech tag to assign, or whether a word is a named entity – is a prediction based on the model’s current weight values. The weight values are estimated based on examples the model has seen during training. To train a model, you first need training data – examples of text, and the labels you want the model to predict. This could be a part-of-speech tag, a named entity or any other information.

Training is an iterative process in which the model’s predictions are compared against the reference annotations in order to estimate the gradient of the loss. The gradient of the loss is then used to calculate the gradient of the weights through backpropagation. The gradients indicate how the weight values should be changed so that the model’s predictions become more similar to the reference labels over time.

The training process

When training a model, we don’t just want it to memorize our examples – we want it to come up with a theory that can be generalized across unseen data. After all, we don’t just want the model to learn that this one instance of “Amazon” right here is a company – we want it to learn that “Amazon”, in contexts like this, is most likely a company. That’s why the training data should always be representative of the data we want to process. A model trained on Wikipedia, where sentences in the first person are extremely rare, will likely perform badly on Twitter. Similarly, a model trained on romantic novels will likely perform badly on legal text.

This also means that in order to know how the model is performing, and whether it’s learning the right things, you don’t only need training data – you’ll also need evaluation data. If you only test the model with the data it was trained on, you’ll have no idea how well it’s generalizing. If you want to train a model from scratch, you usually need at least a few hundred examples for both training and evaluation.

Training config and lifecycle

Training config files include all settings and hyperparameters for training your pipeline. Instead of providing lots of arguments on the command line, you only need to pass your config.cfg file to spacy train. This also makes it easy to integrate custom models and architectures, written in your framework of choice. A pipeline’s config.cfg is considered the “single source of truth”, both at training and runtime.

Illustration of pipeline lifecycle

Trainable components

spaCy’s Pipe class helps you implement your own trainable components that have their own model instance, make predictions over Doc objects and can be updated using spacy train. This lets you plug fully custom machine learning components into your pipeline that can be configured via a single training config.

Illustration of Pipe methods

Language data

Every language is different – and usually full of exceptions and special cases, especially amongst the most common words. Some of these exceptions are shared across languages, while others are entirely specific – usually so specific that they need to be hard-coded. The lang module contains all language-specific data, organized in simple Python files. This makes the data easy to update and extend.

The shared language data in the directory root includes rules that can be generalized across languages – for example, rules for basic punctuation, emoji, emoticons and single-letter abbreviations. The individual language data in a submodule contains rules that are only relevant to a particular language. It also takes care of putting together all components and creating the Language subclass – for example, English or German. The values are defined in the Language.Defaults.

Stop words
List of most common words of a language that are often useful to filter out, for example “and” or “I”. Matching tokens will return True for is_stop.
Tokenizer exceptions
Special-case rules for the tokenizer, for example, contractions like “can’t” and abbreviations with punctuation, like “U.K.”.
Punctuation rules
Regular expressions for splitting tokens, e.g. on punctuation or special characters like emoji. Includes rules for prefixes, suffixes and infixes.
Character classes
Character classes to be used in regular expressions, for example, Latin characters, quotes, hyphens or icons.
Lexical attributes
Custom functions for setting lexical attributes on tokens, e.g. like_num, which includes language-specific words like “ten” or “hundred”.
Syntax iterators
Functions that compute views of a Doc object based on its syntax. At the moment, only used for noun chunks.
Lemmatizer spacy-lookups-data
Custom lemmatizer implementation and lemmatization tables.

Community & FAQ

We’re very happy to see the spaCy community grow and include a mix of people from all kinds of different backgrounds – computational linguistics, data science, deep learning, research and more. If you’d like to get involved, below are some answers to the most important questions and resources for further reading.

Help, my code isn’t working!

Bugs suck, and we’re doing our best to continuously improve the tests and fix bugs as soon as possible. Before you submit an issue, do a quick search and check if the problem has already been reported. If you’re having installation or loading problems, make sure to also check out the troubleshooting guide. Help with spaCy is available via the following platforms:

  • Stack Overflow: Usage questions and everything related to problems with your specific code. The Stack Overflow community is much larger than ours, so if your problem can be solved by others, you’ll receive help much quicker.
  • GitHub discussions: General discussion, project ideas and usage questions. Meet other community members to get help with a specific code implementation, discuss ideas for new projects/plugins, support more languages, and share best practices.
  • GitHub issue tracker: Bug reports and improvement suggestions, i.e. everything that’s likely spaCy’s fault. This also includes problems with the trained pipelines beyond statistical imprecisions, like patterns that point to a bug.

How can I contribute to spaCy?

You don’t have to be an NLP expert or Python pro to contribute, and we’re happy to help you get started. If you’re new to spaCy, a good place to start is the help wanted (easy) label on GitHub, which we use to tag bugs and feature requests that are easy and self-contained. We also appreciate contributions to the docs – whether it’s fixing a typo, improving an example or adding additional explanations. You’ll find a “Suggest edits” link at the bottom of each page that points you to the source.

Another way of getting involved is to help us improve the language data – especially if you happen to speak one of the languages currently in alpha support. Even adding simple tokenizer exceptions, stop words or lemmatizer data can make a big difference. It will also make it easier for us to provide a trained pipeline for the language in the future. Submitting a test that documents a bug or performance issue, or covers functionality that’s especially important for your application is also very helpful. This way, you’ll also make sure we never accidentally introduce regressions to the parts of the library that you care about the most.

For more details on the types of contributions we’re looking for, the code conventions and other useful tips, make sure to check out the contributing guidelines.

I’ve built something cool with spaCy – how can I get the word out?

First, congrats – we’d love to check it out! When you share your project on Twitter, don’t forget to tag @spacy_io so we don’t miss it. If you think your project would be a good fit for the spaCy Universe, feel free to submit it! Tutorials are also incredibly valuable to other users and a great way to get exposure. So we strongly encourage writing up your experiences, or sharing your code and some tips and tricks on your blog. Since our website is open-source, you can add your project or tutorial by making a pull request on GitHub.

If you would like to use the spaCy logo on your site, please get in touch and ask us first. However, if you want to show support and tell others that your project is using spaCy, you can grab one of our spaCy badges here:

Built with spaCy
Made with love and spaCy