mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 03:16:31 +03:00
112 lines
4.1 KiB
Plaintext
112 lines
4.1 KiB
Plaintext
//- 💫 DOCS > USAGE > EXAMPLES
|
||
|
||
include ../_includes/_mixins
|
||
|
||
+section("pipeline")
|
||
+h(3, "custom-components-entities") Custom pipeline components and attribute extensions
|
||
+tag-new(2)
|
||
|
||
p
|
||
| This example shows the implementation of a pipeline component
|
||
| that sets entity annotations based on a list of single or
|
||
| multiple-word company names, merges entities into one token and
|
||
| sets custom attributes on the #[code Doc], #[code Span] and
|
||
| #[code Token].
|
||
|
||
+github("spacy", "examples/pipeline/custom_component_entities.py")
|
||
|
||
+h(3, "custom-components-api")
|
||
| Custom pipeline components and attribute extensions via a REST API
|
||
+tag-new(2)
|
||
|
||
p
|
||
| This example shows the implementation of a pipeline component
|
||
| that fetches country meta data via the
|
||
| #[+a("https://restcountries.eu") REST Countries API] sets entity
|
||
| annotations for countries, merges entities into one token and
|
||
| sets custom attributes on the #[code Doc], #[code Span] and
|
||
| #[code Token] – for example, the capital, latitude/longitude
|
||
| coordinates and the country flag.
|
||
|
||
+github("spacy", "examples/pipeline/custom_component_countries_api.py")
|
||
|
||
+h(3, "custom-components-attr-methods") Custom method extensions
|
||
+tag-new(2)
|
||
|
||
p
|
||
| A collection of snippets showing examples of extensions adding
|
||
| custom methods to the #[code Doc], #[code Token] and
|
||
| #[code Span].
|
||
|
||
+github("spacy", "examples/pipeline/custom_attr_methods.py")
|
||
|
||
+section("matching")
|
||
+h(3, "matcher") Using spaCy's rule-based matcher
|
||
|
||
p
|
||
| This example shows how to use spaCy's rule-based
|
||
| #[+api("matcher") #[code Matcher]] to find and label entities across
|
||
| documents.
|
||
|
||
+github("spacy", "examples/matcher_example.py")
|
||
|
||
+h(3, "phrase-matcher") Using spaCy's phrase matcher
|
||
+tag-new(2)
|
||
|
||
p
|
||
| This example shows how to use the new
|
||
| #[+api("phrasematcher") #[code PhraseMatcher]] to efficiently find
|
||
| entities from a large terminology list.
|
||
|
||
+github("spacy", "examples/phrase_matcher.py")
|
||
|
||
+section("training")
|
||
+h(3, "training-ner") Training spaCy's Named Entity Recognizer
|
||
|
||
p
|
||
| This example shows how to update spaCy's entity recognizer
|
||
| with your own examples, starting off with an existing, pre-trained
|
||
| model, or from scratch using a blank #[code Language] class.
|
||
|
||
+github("spacy", "examples/training/train_ner.py")
|
||
|
||
+h(3, "new-entity-type") Training an additional entity type
|
||
|
||
p
|
||
| This script shows how to add a new entity type to an existing
|
||
| pre-trained NER model. To keep the example short and simple, only
|
||
| four sentences are provided as examples. In practice, you'll need
|
||
| many more — a few hundred would be a good start.
|
||
|
||
+github("spacy", "examples/training/train_new_entity_type.py")
|
||
|
||
+h(3, "textcat") Training spaCy's text classifier
|
||
+tag-new(2)
|
||
|
||
p
|
||
| This example shows how to use and train spaCy's new
|
||
| #[+api("textcategorizer") #[code TextCategorizer]] pipeline component
|
||
| on IMDB movie reviews.
|
||
|
||
+github("spacy", "examples/training/train_textcat.py")
|
||
|
||
+section("deep-learning")
|
||
+h(3, "keras") Text classification with Keras
|
||
|
||
p
|
||
| In this example, we're using spaCy to pre-process text for use with
|
||
| a #[+a("https://keras.io") Keras] text classification model.
|
||
|
||
+github("spacy", "examples/deep_learning_keras.py")
|
||
|
||
+h(3, "keras-parikh-entailment") A decomposable attention model for Natural Language Inference
|
||
|
||
p
|
||
| This example contains an implementation of the entailment prediction
|
||
| model described by #[+a("https://arxiv.org/pdf/1606.01933.pdf") Parikh et al. (2016)].
|
||
| The model is notable for its competitive performance with very few
|
||
| parameters, and was implemented using #[+a("https://keras.io") Keras]
|
||
| and spaCy.
|
||
|
||
+github("spacy", "examples/keras_parikh_entailment/__main__.py", "examples/keras_parikh_entailment")
|