spaCy/website/index.jade

//- 💫 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

    +landing-badge("https://survey.spacy.io", "usersurvey", "Take the user survey!")

    +grid.o-content
        +grid-col("third").o-card
            +h(2) Fastest in the world
            p
                |  spaCy excels 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")
                |  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")
                |  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")
                |  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}

    if LATEST_NEWS
        +a(LATEST_NEWS.url) #[+tag.o-icon New!] #{LATEST_NEWS.title}

.o-content
    +grid
        +grid-col("two-thirds")
            +terminal("lightning_tour.py").
                # Install: pip install spacy && python -m spacy download en
                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")
                    | 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("/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