spaCy

@spacy_io

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

Vrijeme pridruživanja: kolovoz 2015.

Tweetovi

Blokirali ste korisnika/cu @spacy_io

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @spacy_io

  1. Prikvačeni tweet
    2. kol 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

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    A simplistic fun quiz generation using and .It uses named entity recognition on news titles to develop an entity finding trivia . Hope you find it fun.

    Poništi
  3. proslijedio/la je Tweet
    30. sij

    shows us the power of NLP () to interpret legal documents 🔍

    Poništi
  4. proslijedio/la je Tweet
    28. sij

    Introducing the new Thinc, a refreshing functional take on deep learning! 🔮 Static type checking 🔥 Mix , & ⛓️ Integrated config system 🧮 Extensible backends incl. JAX (experimental) 🧬 Variable-length sequences & more

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    26. sij

    Found this cool library that can reverse engineer spacy matcher patterns from data. Will report back after trying it for a few use cases.

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    24. sij

    Have some English text you want to pass to an transformer AND annotate with linguistic metadata from ? Check out to start aligning :)

    Poništi
  7. proslijedio/la je Tweet
    24. sij

    very simple use case of but still pretty awesome to visualize such things; future personal use case is on 8Ks, 10K,Qs, N-Q, 30s ... basically anything in Edgar which can be spaCy-ed also check out prodigy

    Poništi
  8. proslijedio/la je Tweet
    15. sij

    I updated my spacy_conll repo. Parse your text into CoNLL-U format! The plugin can now be used as a custom pipeline component in ! You can still use it from the command-line, too. Thanks to for feedback

    Poništi
  9. proslijedio/la je Tweet
    14. sij

    So glad to talk this Thursday at the in . After the talk, I will give a workshop titled "A dive into : from to Transformers". More info: I will also touch upon and .

    Poništi
  10. proslijedio/la je Tweet
    11. sij

    I published a Finnish language model for : POS tagging and dependency parsing for Finnish on !

    Poništi
  11. proslijedio/la je Tweet
    29. pro 2019.

    I wrote a spaCy NLP tutorial. It even covers transfer learning with BERT! Available in English and Japanese. spaCyのチュートリアルです。GiNZAや日本語BERTも対応。NERデータはのものを使わせていただきました。

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    1. sij

    I did a lot of cool things in 2019, but what I'm most proud of is conquering my fear of public speaking. This conquest resulted in my talk at IRL. If you want to do more public speaking, thread of tips below. 🧵

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet

    Speaking of our team, I just want to note that has been a majority female-run open-source project for quite some time ✊ Core devs: , Adriane (not on Twitter), & me. (Or put differently: we have more female NLP PhDs on our team than guys named Matt.)

    Poništi
  14. proslijedio/la je Tweet
    29. pro 2019.

    What a year! We put together a review with some of the highlights 🎉 Includes: notable releases, talks, great podcasts, and 4 new team members. Thanks for all your support!

    Poništi
  15. proslijedio/la je Tweet

    obligatory is awesome: debug-data just saved me a lot of time because of a dumb preprocessing mistake I made.

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    25. pro 2019.

    As a Christmas present, has made training the algorithm much more memory efficient through lazy loading of the dataset - cf 🎁😎🎄

    Poništi
  17. proslijedio/la je Tweet
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    12. pro 2019.

    🎉 Scispacy, our library/pipeline for biomedical text processing, now has an public demo! 🎉 This builds heavily off 's great demo app, with additional Entity Linking and Specialized NER.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    9. pro 2019.

    💥 New episode of Practical AI! 💬 Modern NLP with SpaCy ⚡️ 🏷 💚

    Poništi
  20. 7. pro 2019.

    Data science instructor Vincent is back with a new episode ✨ In this video you'll learn how to transition a rule-based prototype towards an NER model. Get faster results & a baseline for your machine learning experiments! 📺 Watch it here:

    Poništi
  21. proslijedio/la je Tweet
    3. pro 2019.

    We collect all geopolitical entities through different methods such as rule matching. Shout out to (CC; ) for efficient pipelines, NER and regex + wonderful API

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·