Hicham EL BOUKKOURI

@helboukkouri

I'm a PhD student working on and Word Embeddings at (France). Before that, I studied at and interned at .

France
helboukkouri.github.io/blog/
Vrijeme pridruživanja: studeni 2018.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @helboukkouri

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

  1. proslijedio/la je Tweet
    28. sij

    New paper: Towards a Human-like Open-Domain Chatbot. Key takeaways: 1. "Perplexity is all a chatbot needs" ;) 2. We're getting closer to a high-quality chatbot that can chat about anything Paper: Blog:

    i
    28 replies 629 proslijeđenih tweetova 1.787 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    13. sij

    🔥 Introducing Tokenizers: ultra-fast, extensible tokenization for state-of-the-art NLP 🔥 ➡️

    , , i još njih 3
    11 replies 234 proslijeđena tweeta 980 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    9. pro 2019.

    post-weekend ACL paper status

    27 proslijeđenih tweetova 225 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    1. pro 2019.

    Getting a big scientific prize for open-source software

    29 replies 278 proslijeđenih tweetova 1.238 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    29. stu 2019.

    Open-sourcing a community-focused library basically means you'll keep fighting with a bunch of well-intentioned people who want to morph your simple code in a cathedral of complex and smart abstractions. Writing easy-to-read, simple-to-use code is an under-rated skill.

    13 replies 82 proslijeđena tweeta 604 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    10. stu 2019.

    We release: CamemBERT: a Tasty French Language Model (soon on arxiv) CamemBERT is trained on 138GB of French text. It establishes a new state of the art in POS tagging, Dependency Parsing and NER, and achieves strong results in NLI. Bon appétit ! [1/3]

    19 replies 324 proslijeđena tweeta 882 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    25. lis 2019.

    This is my favorite tweet of all time 🙂I got quite a few new followers so thought I'd share it with you One thing I would add is that `l` and `ll` give you context around the line where exception was raised.

    Favorite recent jupyter notebook discovery - the %debug magic: 1. Get an exception. 2. Insert a new cell, type %debug and run it. An interactive debugger will open bringing you to where the exception occurred and allowing you to look around!
    Prikaži ovu nit
    1 reply 62 proslijeđena tweeta 298 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    25. lis 2019.

    Captum is a state-of-the-art model interpretability library for PyTorch, with algorithms including Integrated Gradients and DeepLIFT. It’s available now on GitHub.

    55 proslijeđenih tweetova 202 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    24. lis 2019.

    The new study by et al. provides a great overview of best practices in the current transfer learning landscape in NLP. Check out page 33 of the paper or below for the main takeaways.

    83 proslijeđena tweeta 345 korisnika označava da im se sviđa
    Poništi
  10. 21. lis 2019.

    Very interesting work by & UCL for analysing the factual and common-sense knowledge that is available in large language models such as BERT, ELMo or GPT-2. Paper: GitHub:

    1 proslijeđeni tweet 3 korisnika označavaju da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    30. ruj 2019.

    🎉 The wait is over! TensorFlow 2.0 is finally here. Driven by community feedback, this release provides a complete set of tools for developers, enterprises, and researchers to easily build ML applications. Read the blog ↓

    36 replies 1.657 proslijeđenih tweetova 3.866 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    25. ruj 2019.

    AllenNLP v0.9.0 is released today. AllenNLP Interpret is the headline feature. We also now have full compatibility with pytorch-transformers from , including RoBERTa (GPT2 and BERT are backing the LM and masked LM in the demos linked below).

    Introducing AllenNLP Interpret: a demo/toolkit for interpreting NLP models. Adversarial attacks, saliency maps, etc. for 𝘢𝘯𝘺 AllenNLP model/task: BERT, SQuAD, NER, ... Demo: Site: w/ [1/7]
    Prikaži ovu nit
    97 proslijeđenih tweetova 302 korisnika označavaju da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    2. kol 2019.

    Yulia Tsvetkov talks about continuous modeling of output spaces (vs. a discrete softmax) at RepL4NLP

    19 proslijeđenih tweetova 113 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    31. srp 2019.

    Thanks to all participants, presenters and volunteers! See you in Seattle for ACL 2020

    8 proslijeđenih tweetova 83 korisnika označavaju da im se sviđa
    Poništi
  15. 29. srp 2019.

    The ACL proceedings are finally out! This means I can finally share with you my paper about improving word embeddings for the biomedical domain: Also, this is the code for reproducing the experiments:

    1 proslijeđeni tweet 7 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    28. srp 2019.

    The tutorial on Unsupervised Cross-lingual learning. , Andreas Soggard, and Ivan Vulic. An important topic.

    19 proslijeđenih tweetova 111 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    12. srp 2019.

    📺 THE VIDEOS FROM ARE NOW LIVE! And we don't mind saying, they turned out great. Here's 12 talks about NLP research, development and applications. Summaries and links in the thread 👇

    6 replies 187 proslijeđenih tweetova 403 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    11. srp 2019.

    Facebook AI and researchers have built Pluribus, the first AI bot to beat elite poker pros in 6 player Texas Hold’em. This breakthrough is the first major benchmark outside of 2 player games and we’re sharing specifics on how we built it.

    475 proslijeđenih tweetova 1.121 korisnik označava da mu se sviđa
    Poništi
  19. proslijedio/la je Tweet
    20. lip 2019.

    RT if you want XLNet in

    232 proslijeđena tweeta 296 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    19. lip 2019.

    “Super interesting, but why would this ever be useful?” is the best feedback I can hope for in research.

    0:00
    Scientists have used CRISPR to store a GIF inside the DNA of a living cell • E.Coli with synthetic strands of DNA, specially designed with sequential information which can then be decoded and turned into a picture, or a series of frames in an animation. 🐎: Seth Shipman
    50 proslijeđenih tweetova 336 korisnika označava da im se sviđa
    Poništi

@helboukkouri još nije objavio nijedan Tweet.

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:

    ·