spaCy

@spacy_io

Open-source library for industrial-strength Natural Language Processing in Python. Developed by 💥 📖 📘 📺

Berlin, Germany
spacy.io
Joined August 2015
119 Photos and videos Photos and videos

Tweets

You blocked @spacy_io

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @spacy_io

  1. Pinned Tweet
    2 Aug 2019

    Say hello to spacy-pytorch-transformers! 🛸 BERT, XLNet & GPT-2 in your spaCy pipeline 🤗 Based on 's pytorch-transformers 🎚️ Fine-tune pretrained models on your task 📦 Model packages for English & German 🚀 Token alignment, similarity & more

    19 replies 444 retweets 1,230 likes
    Show this thread
    Show this thread
    Undo
  2. Retweeted
    May 21

    A beer, sunflower seeds, school assignment and . That's my night.

    1 reply 1 retweet 5 likes
    Undo
  3. Retweeted
    May 18

    The big feature coming in v3 is much better training & model configurability, via our release of . This makes it much easier to have transformer-based pipelines with optional multi-task learning. Preliminary results are pretty encouraging 👇

    5 replies 36 retweets 191 likes
    Show this thread
    Show this thread
    Undo
  4. Retweeted
    May 17

    I released a new version of Finnish model. It supports noun phrase extraction!

    6 retweets 31 likes
    Undo
  5. Retweeted
    May 14

    Wrote up a blog post on how I loaded 20,000 tags into with : /cc

    6 replies 7 retweets 36 likes
    Undo
  6. Retweeted
    May 14

    Recorded a video version of the course! 👩‍🏫🎬 You can watch it as video lessons in the course app, or as one single video tutorial on YouTube, with breaks for exercises. More languages coming soon! 📝 Course: 📺 YouTube:

    6 replies 68 retweets 297 likes
    Show this thread
    Show this thread
    Undo
  7. Retweeted
    May 14

    I've added some features that might make it easier for you to explore whatlies with scikit-learn. There's some caveats due to pickling of backends, but you can easily get some or fasttext into sklearn pipelines.

    3 replies 3 retweets 20 likes
    Show this thread
    Show this thread
    Undo
  8. Retweeted
    May 11

    Really proud to now offer 's spaCy course in 4 languages: English, German, Japanese and now, Spanish 💃 We were incredibly lucky to go to all those years ago in February 2020 🇨🇴. We saw how awesome the Latin Python community is. We hope this helps!

    ¡Nuestro popular curso interactivo en línea ahora en español! Gracias a por la traducción. 📚 4 capítulos: de primeros pasos a tu propio modelo de spaCy 🐍 50 ejercicios interactivos de Python en la web 🎁 100% gratis & código libre
    3 replies 11 retweets 46 likes
    Show this thread
    Show this thread
    Undo
  9. Retweeted
    May 13

    Wrote a small guide on how to package a custom model to work inside of .

    3 retweets 30 likes
    Undo
  10. Retweeted
    May 11

    Using with for automated creation. Very cool!

    Automated AWS Knowledge Graph creation with - check out Senior Full Stack Engineer 's blog post on knowledge graphs here:
    3 retweets 10 likes
    Undo
  11. May 11

    ¡Nuestro popular curso interactivo en línea ahora en español! Gracias a por la traducción. 📚 4 capítulos: de primeros pasos a tu propio modelo de spaCy 🐍 50 ejercicios interactivos de Python en la web 🎁 100% gratis & código libre

    1 reply 30 retweets 64 likes
    Undo
  12. Retweeted
    May 10

    New blog post showing how to customize training parameters from the comfort of your jupyter notebook :)

    5 retweets 10 likes
    Undo
  13. Retweeted
    May 11

    Spacy_conll @ v2! Now w/ tested support for (spacy-)stanza models () and (spacy-)udpipe, easy parser init, Token attributes, and more. Easily parse text w/ stanza, udpipe, or spacy & write to files in four lines!

    2 replies 16 retweets 43 likes
    Undo
  14. Retweeted
    May 8

    Quite an honor to see is (briefly) mentioned in the new "entity linking" tutorial of , one of the top notch nlp platforms out there! uses nlp to extract entities from official company publications and enrich its business network

    📺 NEW VIDEO! In this tutorial, shows how to use spaCy to train a fully custom Entity Linking model to disambiguate different mentions of the person "Emerson" to unique identifiers in a knowledge base. Watch it here:
    Show this thread
    8 retweets 29 likes
    Undo
  15. May 7

    All code and data used in this video is published on GitHub, and you can follow along in a Jupyter notebook:

    3 retweets 15 likes
    Show this thread
    Show this thread
    Undo
  16. May 7

    📺 NEW VIDEO! In this tutorial, shows how to use spaCy to train a fully custom Entity Linking model to disambiguate different mentions of the person "Emerson" to unique identifiers in a knowledge base. Watch it here:

    3 replies 28 retweets 110 likes
    Show this thread
    Show this thread
    Undo
  17. May 6

    spaCyのオンラインコースを日本語で読めるようになりました！（翻訳：） 📚 4章構成: spaCyのモデルの使い方からスタート 🐍 50以上のインタラクティブなPython演習をブラウザ上で 🎁 100%無料のオープンコース

    30 retweets 67 likes
    Undo
  18. Retweeted
    May 5

    This is how using the python code looks like. For people who are doing NLP by looking at dependency trees, its a breeze to integrate, and will likely potentially very nice gains over them.

    1 reply 12 retweets 56 likes
    Undo
  19. Retweeted
    May 3

    I'm happy to share the spacy-annotator: python library to create training data for NER models using ipywidgets. GitHub: Blog post:

    1 reply 7 retweets 41 likes
    Undo
  20. Retweeted
    May 3

    Our new paper on biodiversity & innovation in Antarctica is on bioRxiv . Written in , thanks to bookdown, tidyverse, sparklyr, taxize, tidytext, spacyr, osfr, , , , .

    3 replies 15 retweets 29 likes
    Show this thread
    Show this thread
    Undo
  21. Retweeted
    Apr 30

    Hey 👋 friends, I'm very happy to share Hammurabi, a python rule engine developed @ . It is ✨ compatible, 📝 has its own simple language, & ⚔️ battle-tested for a year. cc:

    10 retweets 45 likes
    Undo

@spacy_io hasn't Tweeted yet.

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·