mixin columns(...names)
  tr
    each name in names
      th= name


mixin row(...cells)
  tr
    each cell in cells
      td= cell


mixin comparison(name)
    details
        summary
            h4 #{name}

        block


+comparison("Peer-reviewed Evaluations")(open=true)

    p spaCy is committed to rigorous evaluation under standard methodology.  Two papers in 2015 confirm that:
    
    ol
        li spaCy is the fastest syntactic parser in the world;
        li Its accuracy is within 1% of the best available;
        li The few systems that are more accurate are 20× slower or more.

    p spaCy v0.84 was evaluated by researchers at Yahoo! Labs and Emory University, as part of a survey paper benchmarking the current state-of-the-art dependency parsers (#[a(href="http://aclweb.org/anthology/P/P15/P15-1038.pdf") Choi et al., 2015]).

    table
        thead
            +columns("System", "Language", "Accuracy", "Speed")

        tbody
            +row("spaCy v0.97", "Cython", "91.8", "13,000 (est.)")
            +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 Discussion with the authors led to accuracy improvements in spaCy, which have been accepted for publication in EMNLP, in joint work with Macquarie University (#[a(href="//aclweb.org/anthology/D/D15/D15-1162.pdf") Honnibal and Johnson, 2015]). 


+comparison("How does spaCy compare to NLTK?")
    .columnar
        .col
            h5 spaCy
            ul
                li.pro Over 400 times faster
                li.pro State-of-the-art accuracy
                li.pro Tokenizer maintains alignment
                li.pro Powerful, concise API
                li.pro Integrated word vectors
                li.con English only (at present)
        .col
            h5 NLTK
            ul
                li.con Slow
                li.con Low accuracy
                li.con Tokens do not align to original string
                li.con Models return lists of strings
                li.con No word vector support
                li.pro Multiple languages


+comparison("How does spaCy compare to CoreNLP?")
    .columnar
        .col
            h5 spaCy
            ul
                li.pro 50% faster
                li.pro More accurate parser
                li.pro Word vectors integration
                li.pro Minimalist design
                li.pro Great documentation
                li.con English only
                li.pro Python
        .col
            h5 CoreNLP
            ul
                li.pro More accurate NER
                li.pro Coreference resolution
                li.pro Sentiment analysis
                li.con Little documentation
                li.pro Multiple languages
                li.neutral Java

+comparison("How does spaCy compare to ClearNLP?")

    .columnar

        .col
            h5 spaCy
            ul
                li.pro 30% faster
                li.pro Well documented
                li.con English only
                li.neutral Equivalent accuracy
                li.pro Python

        .col
            h5 ClearNLP
            ul
                li.pro Semantic Role Labelling
                li.pro Model for biology/life-science
                li.pro Multiple Languages
                li.neutral Equivalent accuracy
                li.neutral Java

//-+comparison("Accuracy Summary")
//-+comparison("Speed Summary")
//-  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 &ndash; 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 &ndash;
//-    | 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)