mirror of https://github.com/explosion/spaCy.git
154 lines
6.6 KiB
Plaintext
154 lines
6.6 KiB
Plaintext
//- 💫 LANDING PAGE
|
|
|
|
include _includes/_mixins
|
|
|
|
+landing-header
|
|
h1.c-landing__title.u-heading-0
|
|
| Industrial-Strength#[br]
|
|
| Natural Language#[br]
|
|
| Processing
|
|
|
|
h2.c-landing__title.o-block.u-heading-1
|
|
| in Python
|
|
|
|
+grid.o-content
|
|
+grid-col("third").o-card
|
|
+h(2) Fastest in the world
|
|
p
|
|
| spaCy excells at large-scale information extraction tasks.
|
|
| It's written from the ground up in carefully memory-managed
|
|
| Cython. Independent research has confirmed that spaCy is
|
|
| the fastest in the world. If your application needs to
|
|
| process entire web dumps, spaCy is the library you want to
|
|
| be using.
|
|
|
|
+button("/docs/api", true, "primary")(target="_self")
|
|
| Facts & figures
|
|
|
|
+grid-col("third").o-card
|
|
+h(2) Get things done
|
|
p
|
|
| spaCy is designed to help you do real work — to build real
|
|
| products, or gather real insights. The library respects
|
|
| your time, and tries to avoid wasting it. It's easy to
|
|
| install, and its API is simple and productive. I like to
|
|
| think of spaCy as the Ruby on Rails of Natural Language
|
|
| Processing.
|
|
|
|
+button("/docs/usage", true, "primary")(target="_self")
|
|
| Get started
|
|
|
|
+grid-col("third").o-card
|
|
+h(2) Deep learning
|
|
p
|
|
| spaCy is the best way to prepare text for deep learning.
|
|
| It interoperates seamlessly with
|
|
| #[+a("https://www.tensorflow.org") TensorFlow],
|
|
| #[+a("https://keras.io") Keras],
|
|
| #[+a("http://scikit-learn.org") Scikit-Learn],
|
|
| #[+a("https://radimrehurek.com/gensim") Gensim] and the
|
|
| rest of Python's awesome AI ecosystem. spaCy helps you
|
|
| connect the statistical models trained by these libraries
|
|
| to the rest of your application.
|
|
|
|
+button("/docs/usage/deep-learning", true, "primary")(target="_self")
|
|
| Read more
|
|
|
|
.o-inline-list.o-block.u-border-bottom.u-text-small.u-text-center.u-padding-small
|
|
+a(gh("spaCy") + "/releases")
|
|
strong.u-text-label.u-color-subtle #[+icon("code", 18)] Latest release:
|
|
| v#{SPACY_VERSION}
|
|
|
|
.o-content
|
|
+grid
|
|
+grid-col("two-thirds")
|
|
+terminal("lightning_tour.py").
|
|
# Install: pip install spacy && python -m spacy.en.download
|
|
import spacy
|
|
|
|
# Load English tokenizer, tagger, parser, NER and word vectors
|
|
nlp = spacy.load('en')
|
|
|
|
# Process a document, of any size
|
|
text = open('war_and_peace.txt').read()
|
|
doc = nlp(text)
|
|
|
|
# Hook in your own deep learning models
|
|
similarity_model = load_my_neural_network()
|
|
def install_similarity(doc):
|
|
doc.user_hooks['similarity'] = similarity_model
|
|
nlp.pipeline.append(install_similarity)
|
|
|
|
doc1 = nlp(u'the fries were gross')
|
|
doc2 = nlp(u'worst fries ever')
|
|
doc1.similarity(doc2)
|
|
|
|
+grid-col("third")
|
|
+h(2) Features
|
|
+list
|
|
+item Non-destructive #[strong tokenization]
|
|
+item Syntax-driven sentence segmentation
|
|
+item Pre-trained #[strong word vectors]
|
|
+item Part-of-speech tagging
|
|
+item #[strong Named entity] recognition
|
|
+item Labelled dependency parsing
|
|
+item Convenient string-to-int mapping
|
|
+item Export to numpy data arrays
|
|
+item GIL-free #[strong multi-threading]
|
|
+item Efficient binary serialization
|
|
+item Easy #[strong deep learning] integration
|
|
+item Statistical models for #[strong English] and #[strong German]
|
|
+item State-of-the-art speed
|
|
+item Robust, rigorously evaluated accuracy
|
|
|
|
.o-inline-list
|
|
+button("/docs/usage/lightning-tour", true, "secondary")(target="_self")
|
|
| See examples
|
|
|
|
.o-block.u-text-center.u-padding
|
|
h3.u-text-label.u-color-subtle.o-block spaCy is trusted by
|
|
|
|
each row in logos
|
|
+grid("center").o-inline-list
|
|
each details, name in row
|
|
+a(details[0])
|
|
img(src="/assets/img/logos/#{name}.png" alt=name width=(details[1] || 150)).u-padding-small
|
|
|
|
.u-pattern.u-padding
|
|
+grid.o-card.o-content
|
|
+grid-col("quarter")
|
|
img(src="/assets/img/profile_matt.png" width="280")
|
|
|
|
+grid-col("three-quarters")
|
|
+h(2) What's spaCy all about?
|
|
|
|
p
|
|
| By 2014, I'd been publishing NLP research for about 10
|
|
| years. During that time, I saw a huge gap open between the
|
|
| technology that Google-sized companies could take to market,
|
|
| and what was available to everyone else. This was especially
|
|
| clear when companies started trying to use my research. Like
|
|
| most researchers, my work was free to read, but expensive to
|
|
| apply. You could run my code, but its requirements were
|
|
| narrow. My code's mission in life was to print results
|
|
| tables for my papers — it was good at this job, and bad at
|
|
| all others.
|
|
|
|
p
|
|
| spaCy's #[a(href="/docs/api/philosophy") mission] is to make
|
|
| cutting-edge NLP practical and commonly available. That's
|
|
| why I left academia in 2014, to build a production-quality
|
|
| open-source NLP library. It's why
|
|
| #[+a("https://twitter.com/_inesmontani") Ines] joined the
|
|
| project in 2015, to build visualisations, demos and
|
|
| annotation tools that make NLP technologies less abstract
|
|
| and easier to use. Together, we've founded
|
|
| #[+a(COMPANY_URL, true) Explosion AI], to develop data packs
|
|
| you can drop into spaCy to extend its capabilities. If
|
|
| you're processing Hindi insurance claims, you need a model
|
|
| for that. We can build it for you.
|
|
|
|
.o-block
|
|
+a("https://twitter.com/honnibal")
|
|
+svg("graphics", "matt-signature", 60, 45).u-color-theme
|