Bram Vanroy

@BramVanroy

Doctoral researcher in at LT3, . Open-source fanatic, contributing where I can. Quite active in ML/DL/NLP on and

Ghent, Belgium
Vrijeme pridruživanja: kolovoz 2011.

Tweetovi

Blokirali ste korisnika/cu @BramVanroy

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

  1. Prikvačeni 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
  2. proslijedio/la je Tweet
    3. velj
    Poništi
  3. proslijedio/la je Tweet
    2. velj
    Odgovor korisniku/ci

    A PhD is definitely not required. All that matters is a deep understanding of AI & ability to implement NNs in a way that is actually useful (latter point is what’s truly hard). Don’t care if you even graduated high school.

    Poništi
  4. 2. velj

    Unfortunately, using spacy-stanfordnlp gives slightly less control over pretokenisation and dis/enabling sentence segmentation in a mutually exclusive manner.

    Prikaži ovu nit
    Poništi
  5. 2. velj

    Changes to my extension spacy_conll: expanded docs on how to use w/ models by using spacy-stanfordnlp to get "real" UD results. Added option for custom tagset mapping in case you have your own tagset mapping.

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

    Turkish-: Anyone interested in a Turkish BERT and wants to evaluate it on downstream tasks? I did evaluation only for UD PoS tagging - any help is really appreciated! Would really like to have a proper evaluation before adding it to the Transformers hub🤗

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

    Proud to say that our BERTje from is now available as the default Dutch BERT model in Transformers by ! Some comparisons of BERTje with mBERT, BERT-NL and RobBERT are available on (more coming soon).

    Poništi
  8. proslijedio/la je Tweet
    30. sij

    Pandas 1.0 is here! * Read the release notes: * Read the blogpost reflecting on what 1.0 means to our project: * Install with conda / PyPI: Thanks to our 300+ contributors to this release.

    Poništi
  9. 30. sij

    . presenting her work on automatic writing evaluation at CLIN

    Poništi
  10. 30. sij

    Our research group LT3 is present in numbers at ! Talks and posters by , Sofie Labat, Jasper Degraeuwe, Patrick Goethals, Margot Fonteyne, Ayla R. Terryn.

    Poništi
  11. proslijedio/la je Tweet
    21. sij

    OPUS-MT (): over 1,000 pre-trained translation models and a dockerized translation server based on

    Poništi
  12. proslijedio/la je Tweet
    23. sij

    Google Dataset Search is now officially out of beta. "Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is." Nice work, Natasha Noy and everyone else involved!

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    20. sij

    We are proud to present our Dutch BERT model called RobBERT, achieving state-of-the-art results for several Dutch language tasks (w/ ) 📝 Paper: 🤖 Model & Code: 🌐 Website:

    Prikaži ovu nit
    Poništi
  14. 16. sij

    This is progress. Reformer can process context windows of up to 1M words on a single 16GB device! "Reformer can process entire novels, all at once and on a single device." Looking forward to the talk and paper.

    Poništi
  15. proslijedio/la je Tweet
    15. sij
    Poništi
  16. proslijedio/la je Tweet
    4. sij
    Poništi
  17. proslijedio/la je Tweet
    6. sij

    Hello! We are looking for native speakers of Italian living in English-speaking countries to take part in a short (about 15 min) and anonymous online survey. Our goal is to understand your opinions of (translated) messages aimed at preparing the public in case of flooding.

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

    Oh, and I also wish to learn more about evaluating and visualizing the impact of different layers and latent features in a . If you have any experience with that, please share tools and papers!

    Prikaži ovu nit
    Poništi
  19. 1. sij

    Oh, and I also wish to learn more about evaluating and visualizing the impact of different layers and latent features in a . If you have any experience with that, please share tools and papers!

    Prikaži ovu nit
    Poništi
  20. 1. sij

    What I wanna try in 2020 - or fastAPI - after seeing talk by . I only know Java Python Perl and web languages so this'll be a challenge - build a based translation difficulty predicting system

    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:

    ·