mirror of https://github.com/explosion/spaCy.git
* Work on landing page in jade
This commit is contained in:
Matthew Honnibal
parent
bf38b3b883
commit
a3290a5810
|
|
@ -0,0 +1,263 @@
|
|||
- var slogan = "Build Tomorrow's Language Technologies"
|
||||
- var tag_line = "spaCy – #{slogan}"
|
||||
- var a_minor_miracle = '<a href="">a minor miracle</a>'
|
||||
|
||||
mixin lede()
|
||||
p.
|
||||
<strong>spaCy</strong> is a library for industrial-strength NLP in Python and
|
||||
Cython. It features state-of-the-art speed and accuracy, a concise API, and
|
||||
great documentation. If you're a small company doing NLP, we want spaCy to
|
||||
seem like !{a_minor_miracle}.
|
||||
|
||||
mixin overview()
|
||||
p.
|
||||
Overview text
|
||||
|
||||
mixin example()
|
||||
p.
|
||||
Example text
|
||||
|
||||
mixin benchmarks()
|
||||
p.
|
||||
Benchmarks
|
||||
|
||||
mixin get_started()
|
||||
p.
|
||||
Get Started
|
||||
|
||||
mixin example(name)
|
||||
details
|
||||
summary
|
||||
span(class="example-name")= name
|
||||
|
||||
block
|
||||
|
||||
|
||||
mixin accuracy_head
|
||||
tr
|
||||
|
||||
mixin columns(...names)
|
||||
tr
|
||||
each name in names
|
||||
th= name
|
||||
|
||||
|
||||
mixin row(...cells)
|
||||
tr
|
||||
each cell in cells
|
||||
td= cell
|
||||
|
||||
|
||||
doctype html
|
||||
html(lang="en")
|
||||
head
|
||||
meta(charset="utf-8")
|
||||
title!= tag_line
|
||||
meta(name="description" content="")
|
||||
meta(name="author" content="Matthew Honnibal")
|
||||
link(rel="stylesheet" href="css/style.css")
|
||||
<!--[if lt IE 9]>
|
||||
script(src="http://html5shiv.googlecode.com/svn/trunk/html5.js")
|
||||
<![endif]-->
|
||||
|
||||
body(id="page" role="document")
|
||||
header(role="banner")
|
||||
h1(class="logo")!= tag_line
|
||||
div(class="slogan")!= slogan
|
||||
|
||||
nav(role="navigation")
|
||||
ul
|
||||
li: a(href="#") Home
|
||||
li: a(href="#") Docs
|
||||
li: a(href="#") License
|
||||
li: a(href="#") Blog
|
||||
|
||||
main(id="content" role="main")
|
||||
section(class="intro")
|
||||
+lede
|
||||
|
||||
nav(role="navigation")
|
||||
ul
|
||||
li: a(href="#overview" class="button") Examples
|
||||
li: a(href="#overview" class="button") Comparisons
|
||||
li: a(href="#example-use" class="button") Demo
|
||||
li: a(href="#get-started" class="button") Install
|
||||
|
||||
article(class="page landing-page")
|
||||
a(name="example-use"): h3 Usage by Example
|
||||
|
||||
+example("Load resources and process text")
|
||||
pre.language-python
|
||||
code
|
||||
| from __future__ import unicode_literals, print_function
|
||||
| from spacy.en import English
|
||||
| nlp = English()
|
||||
| doc = nlp('Hello, world. Here are two sentences.')
|
||||
|
||||
+example("Get tokens and sentences")
|
||||
pre.language-python
|
||||
code
|
||||
| token = doc[0]
|
||||
| sentence = doc.sents[0]
|
||||
| assert token[0] is sentence[0]
|
||||
|
||||
+example("Use integer IDs for any string")
|
||||
pre.language-python
|
||||
code
|
||||
| hello_id = nlp.vocab.strings['Hello']
|
||||
| hello_str = nlp.vocab.strings[hello_id]
|
||||
|
|
||||
| assert token.orth == hello_id == 52
|
||||
| assert token.orth_ == hello_str == 'Hello'
|
||||
|
||||
+example("Get and set string views and flags")
|
||||
pre.language-python
|
||||
code
|
||||
| assert token.shape_ == 'Xxxx'
|
||||
| for lexeme in nlp.vocab:
|
||||
| if lexeme.is_alpha:
|
||||
| lexeme.shape_ = 'W'
|
||||
| elif lexeme.is_digit:
|
||||
| lexeme.shape_ = 'D'
|
||||
| elif lexeme.is_punct:
|
||||
| lexeme.shape_ = 'P'
|
||||
| else:
|
||||
| lexeme.shape_ = 'M'
|
||||
| assert token.shape_ == 'W'
|
||||
|
||||
+example("Export to numpy arrays")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Word vectors")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Part-of-speech tags")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Syntactic dependencies")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Named entities")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Define custom NER rules")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Calculate inline mark-up on original string")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
+example("Efficient binary serialization")
|
||||
pre.language-python
|
||||
code
|
||||
| Do me
|
||||
|
||||
a(name="benchmarks"): h3 Benchmarks
|
||||
|
||||
details
|
||||
summary: h4 Independent Evaluation
|
||||
|
||||
p
|
||||
| Independent evaluation by Yahoo! Labs and Emory
|
||||
| University, to appear at ACL 2015. Higher is better.
|
||||
|
||||
table
|
||||
thead
|
||||
+columns("System", "Language", "Accuracy", "Speed")
|
||||
|
||||
tbody
|
||||
+row("spaCy v0.86", "Cython", "91.9", "13,963")
|
||||
+row("spaCy v0.84", "Cython", "90.6", "13,963")
|
||||
+row("ClearNLP", "Java", "91.7", "10,271")
|
||||
+row("CoreNLP", "Java", "89.6", "8,602")
|
||||
+row("MATE", "Java", "92.5", "550")
|
||||
+row("Turbo", "C++", "92.4", "349")
|
||||
+row("Yara", "Java", "92.3", "340")
|
||||
|
||||
p
|
||||
| Accuracy is % unlabelled arcs correct, speed is tokens per second.
|
||||
|
||||
p
|
||||
| Joel Tetreault and Amanda Stent (Yahoo! Labs) and Jin-ho Choi (Emory)
|
||||
| performed a detailed comparison of the best parsers available.
|
||||
| All numbers above are taken from the pre-print they kindly made
|
||||
| available to me, except for spaCy v0.86.
|
||||
|
||||
p
|
||||
| I'm particularly grateful to the authors for discussion of their
|
||||
| results, which led to the improvement in accuracy between v0.84 and
|
||||
| v0.86. A tip from Jin-ho developer of ClearNLP) was particularly
|
||||
| useful.
|
||||
|
||||
details
|
||||
summary: h4 Detailed Accuracy Comparison
|
||||
|
||||
details
|
||||
summary: h4 Detailed Speed Comparison
|
||||
|
||||
table
|
||||
thead
|
||||
tr
|
||||
th.
|
||||
th(colspan=3) Absolute (ms per doc)
|
||||
th(colspan=3) Relative (to spaCy)
|
||||
|
||||
tbody
|
||||
tr
|
||||
td: strong System
|
||||
td: strong Split
|
||||
td: strong Tag
|
||||
td: strong Parse
|
||||
td: strong Split
|
||||
td: strong Tag
|
||||
td: strong Parse
|
||||
|
||||
+row("spaCy", "0.2ms", "1ms", "19ms", "1x", "1x", "1x")
|
||||
+row("spaCy", "0.2ms", "1ms", "19ms", "1x", "1x", "1x")
|
||||
+row("CoreNLP", "2ms", "10ms", "49ms", "10x", "10x", "2.6x")
|
||||
+row("ZPar", "1ms", "8ms", "850ms", "5x", "8x", "44.7x")
|
||||
+row("NLTK", "4ms", "443ms", "n/a", "20x", "443x", "n/a")
|
||||
|
||||
p
|
||||
| <strong>Set up</strong>: 100,000 plain-text documents were streamed
|
||||
| from an SQLite3 database, and processed with an NLP library, to one
|
||||
| of three levels of detail – tokenization, tagging, or parsing.
|
||||
| The tasks are additive: to parse the text you have to tokenize and
|
||||
| tag it. The pre-processing was not subtracted from the times –
|
||||
| I report the time required for the pipeline to complete. I report
|
||||
| mean times per document, in milliseconds.
|
||||
|
||||
p
|
||||
| <strong>Hardware</strong>: Intel i7-3770 (2012)
|
||||
|
||||
|
||||
//+comparison("spaCy vs. NLTK")
|
||||
//+comparison("spaCy vs. Pattern")
|
||||
//+comparison("spaCy vs. CoreNLP")
|
||||
//+comparison("spaCy vs. ClearNLP")
|
||||
//+comparison("spaCy vs. OpenNLP")
|
||||
//+comparison("spaCy vs. GATE")
|
||||
|
||||
a(name="get-started"): h3 Get started
|
||||
|
||||
+get_started
|
||||
|
||||
|
||||
|
||||
|
||||
footer(role="contentinfo")
|
||||
|
||||
script(src="js/prism.js")
|
||||
Loading…
Reference in New Issue