Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
spaCy
open-in-new
<h2 id="history">History</h2> <ul><li>Version 1.0 was released on October 19, 2016, and included preliminary support for deep learning workflows by supporting custom processing pipelines.<a class="footnote-ref" id="fnref:8" href="#fn:8"><sup>8</sup></a> It further included a rule matcher that supported <a href="/facts/Named_entity/pqC6pucA">entity</a> annotations, and an officially documented training API.</li> <li>Version 2.0 was released on November 7, 2017, and introduced convolutional neural network models for 7 different languages.<a class="footnote-ref" id="fnref:9" href="#fn:9"><sup>9</sup></a> It also supported custom processing pipeline components and extension attributes, and featured a built-in trainable <a href="/facts/Text_classification/B69lL6BH">text classification</a> component.</li> <li>Version 3.0 was released on February 1, 2021, and introduced state-of-the-art <a href="/facts/Transformer_(machine_learning_model)/cDbjx6a8">transformer</a>-based pipelines.<a class="footnote-ref" id="fnref:10" href="#fn:10"><sup>10</sup></a> It also introduced a new configuration system and training workflow, as well as type hints and project templates. This version dropped support for <a href="/facts/Python_2/BJsrzTle">Python 2</a>.</li></ul> <h2 id="main-features">Main features</h2> <ul><li>Non-destructive <a href="/facts/Tokenization_(lexical_analysis)/T1JYWpIf">tokenization</a></li> <li>"Alpha tokenization" support for over 65 languages<a class="footnote-ref" id="fnref:11" href="#fn:11"><sup>11</sup></a></li> <li>Built-in support for trainable pipeline components such as <a href="/facts/Named-entity_recognition/ko6GRQQd">Named entity recognition</a>, <a href="/facts/Part-of-speech_tagging/BYAPmH3r">Part-of-speech tagging</a>, <a href="/facts/Dependency_grammar/cWnwcCM0">dependency</a> parsing, <a href="/facts/Document_classification/B69lL6BH">Text classification</a>, <a href="/facts/Entity_Linking/bg9hGSVY">Entity Linking</a> and more</li> <li><a href="/facts/Statistical_model/jKkT5ftm">Statistical models</a> for 19 languages<a class="footnote-ref" id="fnref:12" href="#fn:12"><sup>12</sup></a></li> <li><a href="/facts/Multi-task_learning/av9lCQUF">Multi-task learning</a> with pretrained transformers like <a href="/facts/BERT_(language_model)/rDSueM4E">BERT</a></li> <li>Support for custom models in PyTorch, TensorFlow and other frameworks</li> <li>State-of-the-art speed and accuracy<a class="footnote-ref" id="fnref:13" href="#fn:13"><sup>13</sup></a></li> <li>Production-ready training system</li> <li>Built-in visualizers for <a href="/facts/Syntax/6PxSV98p">syntax</a> and <a href="/facts/Named-entity_recognition/ko6GRQQd">named entities</a></li> <li>Easy model packaging, deployment and workflow management</li></ul> <h2 id="extensions-and-visualizers">Extensions and visualizers</h2> <p>spaCy comes with several extensions and visualizations that are available as free, <a href="/facts/Open-source_software/HzTaB8E9">open-source</a> libraries: </p> <ul><li>Thinc: A <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a> library optimized for <a href="/facts/Central_processing_unit/Jxp1bqMV">CPU</a> usage and <a href="/facts/Deep_learning/JLuwD3ea">deep learning</a> with text input.</li> <li>sense2vec: A library for computing word similarities, based on <a href="/facts/Word2vec/DAuubBYX">Word2vec</a>.<a class="footnote-ref" id="fnref:14" href="#fn:14"><sup>14</sup></a></li> <li>displaCy: An <a href="/facts/Open-source_software/HzTaB8E9">open-source</a> dependency <a href="/facts/Parse_tree/FeBEtXcz">parse tree</a> visualizer built with <a href="/facts/JavaScript/XhhIIEsl">JavaScript</a>, <a href="/facts/Cascading_Style_Sheets/tA90XBQo">CSS</a> and <a href="/facts/Scalable_Vector_Graphics/ARq5C3YV">SVG</a>.</li> <li>displaCyENT: An <a href="/facts/Open-source_software/HzTaB8E9">open-source</a> <a href="/facts/Named-entity_recognition/ko6GRQQd">named entity</a> visualizer built with <a href="/facts/JavaScript/XhhIIEsl">JavaScript</a> and <a href="/facts/Cascading_Style_Sheets/tA90XBQo">CSS</a>.</li></ul> <h2 id="external-links">External links</h2> <ul><li><a href="https://spacy.io">Official website</a> </li> <li><a href="https://www.presentslide.in/2019/07/implementing-spacy-advanced-natural-language-processing.html">Implementing Spacy Library</a></li></ul> <h2 id="references">References</h2> <ol> <li id="fn:1"><p>Choi et al. (2015). It Depends: Dependency Parser Comparison Using A Web-based Evaluation Tool. <a href="https://aclweb.org/anthology/P/P15/P15-1038.pdf" target="_blank">https://aclweb.org/anthology/P/P15/P15-1038.pdf</a> <a href="#fnref:1" class="footnote-back-ref">↩</a></p></li> <li id="fn:2"><p>"Google's new artificial intelligence can't understand these sentences. Can you?". Washington Post. Retrieved 2016-12-18. <a href="https://www.washingtonpost.com/news/wonk/wp/2016/05/18/googles-new-artificial-intelligence-cant-understand-these-sentences-can-you/" target="_blank">https://www.washingtonpost.com/news/wonk/wp/2016/05/18/googles-new-artificial-intelligence-cant-understand-these-sentences-can-you/</a> <a href="#fnref:2" class="footnote-back-ref">↩</a></p></li> <li id="fn:3"><p>"Facts & Figures - spaCy". spacy.io. Retrieved 2020-04-04. <a href="https://spacy.io/usage/facts-figures#other-libraries" target="_blank">https://spacy.io/usage/facts-figures#other-libraries</a> <a href="#fnref:3" class="footnote-back-ref">↩</a></p></li> <li id="fn:4"><p>Bird, Steven; Klein, Ewan; Loper, Edward; Baldridge, Jason (2008). "Multidisciplinary instruction with the Natural Language Toolkit" (PDF). Proceedings of the Third Workshop on Issues in Teaching Computational Linguistics, ACL: 62. doi:10.3115/1627306.1627317. ISBN 9781932432145. S2CID 16932735. <a href="9781932432145" target="_blank">9781932432145</a> <a href="#fnref:4" class="footnote-back-ref">↩</a></p></li> <li id="fn:5"><p>"PyTorch, TensorFlow & MXNet". thinc.ai. Retrieved 2020-04-04. <a href="https://thinc.ai/docs/usage-frameworks" target="_blank">https://thinc.ai/docs/usage-frameworks</a> <a href="#fnref:5" class="footnote-back-ref">↩</a></p></li> <li id="fn:6"><p>"explosion/thinc". GitHub. Retrieved 2016-12-30. <a href="https://github.com/explosion/thinc" target="_blank">https://github.com/explosion/thinc</a> <a href="#fnref:6" class="footnote-back-ref">↩</a></p></li> <li id="fn:7"><p>"Models & Languages | spaCy Usage Documentation". spacy.io. Retrieved 2020-03-10. <a href="https://spacy.io/usage/models#languages" target="_blank">https://spacy.io/usage/models#languages</a> <a href="#fnref:7" class="footnote-back-ref">↩</a></p></li> <li id="fn:8"><p>"explosion/spaCy". GitHub. Retrieved 2021-02-08. <a href="https://github.com/explosion/spaCy/releases/tag/v1.0.0" target="_blank">https://github.com/explosion/spaCy/releases/tag/v1.0.0</a> <a href="#fnref:8" class="footnote-back-ref">↩</a></p></li> <li id="fn:9"><p>"explosion/spaCy". GitHub. Retrieved 2021-02-08. <a href="https://github.com/explosion/spaCy/releases/tag/v2.0.0" target="_blank">https://github.com/explosion/spaCy/releases/tag/v2.0.0</a> <a href="#fnref:9" class="footnote-back-ref">↩</a></p></li> <li id="fn:10"><p>"explosion/spaCy". GitHub. Retrieved 2021-02-08. <a href="https://github.com/explosion/spaCy/releases/tag/v3.0.0" target="_blank">https://github.com/explosion/spaCy/releases/tag/v3.0.0</a> <a href="#fnref:10" class="footnote-back-ref">↩</a></p></li> <li id="fn:11"><p>"Models & Languages - spaCy". spacy.io. Retrieved 2021-02-08. <a href="https://spacy.io/usage/models" target="_blank">https://spacy.io/usage/models</a> <a href="#fnref:11" class="footnote-back-ref">↩</a></p></li> <li id="fn:12"><p>"Models & Languages | spaCy Usage Documentation". spacy.io. Retrieved 2021-02-08. <a href="https://spacy.io/usage/models" target="_blank">https://spacy.io/usage/models</a> <a href="#fnref:12" class="footnote-back-ref">↩</a></p></li> <li id="fn:13"><p>"Benchmarks | spaCy Usage Documentation". spacy.io. Retrieved 2021-02-08. <a href="https://spacy.io/usage/facts-figures#benchmarks" target="_blank">https://spacy.io/usage/facts-figures#benchmarks</a> <a href="#fnref:13" class="footnote-back-ref">↩</a></p></li> <li id="fn:14"><p>Trask et al. (2015). sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings. <a href="https://arxiv.org/abs/1511.06388" target="_blank">https://arxiv.org/abs/1511.06388</a> <a href="#fnref:14" class="footnote-back-ref">↩</a></p></li> </ol>