UW NLP

@uwnlp

The NLP group at the University of Washington.

Vrijeme pridruživanja: rujan 2015.

Tweetovi

Blokirali ste korisnika/cu @uwnlp

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

  1. proslijedio/la je Tweet
    31. sij

    AKBC 2020 Abstract Deadline (February 6) is next week! Full papers are due Feb 13th! Please submit your finest work to the conference. Website () has been updated with submission details.

    Poništi
  2. proslijedio/la je Tweet
    28. sij

    Wrote up a blog post on non-autoregressive machine translation! Hope this gives you a sense of what is happening in the exciting area of research!

    Poništi
  3. 22. sij

    Watch 's talk "How will we know when machines can read?" last month

    Poništi
  4. proslijedio/la je Tweet
    16. sij

    Proposed the DisCo transformer, an efficient alternative to masked LMs for non-autoregressive translation. Special thanks to my coauthors James Cross, , and friends , for inspiring me to do MT.

    Poništi
  5. proslijedio/la je Tweet
    13. sij

    CfP for the workshop on Advances in Language and Vision Research (ALVR) at ! We're excited for papers exploring active perception, real language, and photo-realistic simulation (or even real world) action spaces. Submission deadline April 6.

    Poništi
  6. proslijedio/la je Tweet
    19. pro 2019.

    Check out our latest work, DeFINE: Deep Factorized Input word Representations, accepted at . DeFINe is as efficient as existing methods such as Adaptive Inputs from , but delivers better performance. Work done at

    Poništi
  7. proslijedio/la je Tweet
    16. pro 2019.

    What even is commonsense🤔?? Come find out at our tutorial 🙋on Commonsense Reasoning for NLP! With , , from & and Dan Roth from UPenn!

    Poništi
  8. proslijedio/la je Tweet
    12. pro 2019.

    Excited to talk about our new benchmark for interpreting grounded, natural language instructions for a simulated agent to accomplish household tasks. I'll be presenting tomorrow, Dec 13 at 9:10am during the ViGIL workshop in West 202-204 at .

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

    Here's the complete list of tutorials to be held on Sunday July 5, 2020.

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    5. pro 2019.

    New work with Kazuma Hashimoto, , , and at and ! Our trainable graph-based retriever-reader framework for open-domain QA advances state of the art on HotpotQA, SQuAD Open, Natural Questions Open. 👇1/7

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    27. stu 2019.

    Hey, so we took a stab at trying to build a task that looks at physical commonsense (). The data was specifically made to be adversarial to BERT, but RoBERTa still leaves a lot to be desired (). Author's Note(s): ...

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    27. stu 2019.

    PIQA: Reasoning about Physical Commonsense in Natural Language by Yonatan Bisk et al. including

    Poništi
  13. proslijedio/la je Tweet
    19. stu 2019.

    Sam Bowman is giving an invited talk at ! Check out the live video at

    Poništi
  14. proslijedio/la je Tweet
    19. stu 2019.

    live now: NYU's speaking at "Evaluating Recent Progress Toward General-Purpose Language Understanding Models"

    Poništi
  15. proslijedio/la je Tweet
    8. stu 2019.

    Transformers are made of interleaved self-attention and feedforward sublayers. Can we find a better pattern? New work on *improving transformers by reordering their sublayers* with and

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    7. stu 2019.
    Odgovor korisnicima
    Poništi
  17. proslijedio/la je Tweet
    5. stu 2019.

    Check out our talk tomorrow (Wednesday) at 14:42-15:00, AWE 201, "A Discrete Hard EM Approach for Weakly Supervised Question Answering" with

    Poništi
  18. proslijedio/la je Tweet
    4. stu 2019.

    Good morning ! I'm not there, but will give an awesome talk this afternoon on training tiny models for goal-directed vision. Save those precious parameters, use them somewhere else. Award Session II -- 15:00-15:15, TuBT4.2

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    2. stu 2019.

    🍾Information Bottleneck🍾 in action at ! (1) Specializing embeddings for parsing () by Xiang & (2) 🍾BottleSum🍾 unsupervised & self-supervised summarization () with

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    2. stu 2019.

    Lianhui (Karen) will give a talk at⏱: Nov 7 Wed 13:30–13:48 and 🏢: AWE HALL 2C with at and

    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:

    ·