Yejin Choi

@YejinChoinka

professor at UW, research manager at AI2, adventurer at heart

Vrijeme pridruživanja: kolovoz 2017.

Tweetovi

Blokirali ste korisnika/cu @YejinChoinka

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

  1. Prikvačeni tweet
    2. stu 2019.

    The⏱TimeTravel⏱dataset of our paper, 🎞Counterfactual Story Reasoning and Generation🎞 () tests counterfactual reasoning over events that unfold over time, directly addressing 's call for a challenge against current neural models....

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    1. velj

    Just found out about WinoGrande, really cool effort! I like how authors (, Ronan Le Bras, Chandra Bhagavatula, ) advocate for 'dynamic' benchmarks; with so many datasets being introduced all the time, feels like the next step.

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    Reduce Bias in Text? Find it out in our podcast with 📢

    Poništi
  4. proslijedio/la je Tweet
    31. sij

    WinoGrande, a new dataset by researchers on AI2's team, was created in pursuit of generalizable . 's covers the challenges of building that can truly understand human language:

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

    Excited that our work on characterizing racial bias in football commentary was covered by ! Thanks to for thoroughly explaining and contextualizing our research to a non-academic audience. We're continuing with this work, so look out for more soon!

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

    Video & slides for LIRE workshop @ are now up: Check out the Talks and Panel by Jeff Bilmes Tom Griffiths & more. Thanks to all speakers & presenters for making the workshop a success!

    , , i još njih 3
    Poništi
  7. proslijedio/la je Tweet
    17. stu 2019.

    Thanks Joelle Pineau and for having me as the keynote speaker at Facebook Women in AI Summit, sharing my experience with so many great women AI researchers & engineers! Here's the book by I recommended as a must-read for every woman: .

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

    In my talk on "Grasping Language" at the NeurIPS ViGIL workshop, I argue not only that language grounding research is exciting, but also try to make a pitch for language as a rather special modality for sorting out human intelligence. Video/slides here:

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

    The KR2ML Workshop is today! Schedule attached below - we have a superb slate of invited speakers including , Luna Dong, , , , . More info:

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

    Come join the workshop on Learning with Rich Experience. Note the location: West 208+209. Look fwd to the super exciting talks by JeffBilmes & TomGriffiths, and the contributed presentations:

    , , i još njih 5
    Poništi
  13. proslijedio/la je Tweet
    4. pro 2019.

    . & I are co-organizing the next Conference Apr 1, 2020—no joke!—on the topic Triangulating Intelligence: Melding Neuroscience, Psychology, and AI. Botvinick——Tenenbaum——save the date!

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

    We have a postdoc position available! Come join our project on using NLP and speech to help improve police-community relations!

    Poništi
  15. 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
  16. proslijedio/la je Tweet
    27. stu 2019.

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

    Poništi
  17. proslijedio/la je Tweet
    25. stu 2019.

    This has been 2 years and 3 papers in the making: direct mapping of natural language instructions and first-person observations to continuous velocity control. Yep, we learn the entire pipeline with a single interpretable neural model! ❤️

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

    Can reduce bias in our news and politics? Automatically Neutralizing Subjective Bias in Text Pryzant, , … Parallel corpus of 180k biased and neutralized sentences Models for editing subjective bias out of text

    Poništi
  20. proslijedio/la je Tweet
    25. stu 2019.

    Our recent work looks at neutralizing subjective in text. It also releases a parallel corpus of 180K biased/unbiased sentence pairs mined from

    Poništi
  21. proslijedio/la je Tweet
    16. stu 2019.

    The very impressive new ConvoKit from and his Cornell NLP crew provides easy access to lots of conversational datasets and tools:

    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:

    ·