Daniel Adiwardana

@xpearhead

Researching conversational AI at Google Brain Team .

Joined May 2009

Tweets

You blocked @xpearhead

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @xpearhead

  1. Pinned Tweet
    Jan 28

    Enabling people to converse with chatbots about anything has been a passion of a lifetime for me, and I'm sure of others as well. So I'm very thankful to be able to finally share our results with you all. Hopefully, this will help inform efforts in the area. (1/4)

    Show this thread
    Undo
  2. Retweeted
    Jan 29

    This video explains 's amazing new Meena chatbot! An Evolved Transformer with 2.6B parameters on 341 GB / 40B words of conversation data to achieves remarkable chatbot performance! "Horses go to Hayvard!"

    Undo
  3. Retweeted
    Jan 29

    Had the chance to sit next to Daniel in the early days of the project and tried out the interactive Meena. It has always been *this* surprising and funny :) BIG Congrats to the team with this publication. The possibilities to build up from here is endless.

    Undo
  4. Retweeted
    Jan 28

    Meena: new SOTA chatbot from us. One big step towards human-like conversation AI. Look forward to many applications related to that, e.g. 7/24 AI based foreign language tutoring.

    Undo
  5. Retweeted
    Jan 28

    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:

    Show this thread
    Undo
  6. Retweeted
    Jan 28

    Open-domain conversation is an extremely difficult task for ML systems. Meena is a research effort at in this area. It's challenging, but we are making progress towards more fluent and sensible conversations. Nice work, Daniel, & everyone involved!

    Undo
  7. Jan 28

    Bonus: Meena often seems to put together ideas in ways that we don't manage to find matches of in the data. For example saying that "Horses go to Hayvard" in conversation we show in the blog post .

    Show this thread
    Undo
  8. Jan 28

    "It was trained on movie subtitles?!" I told myself and others in awe. Maybe the potential for generalization was really there. I was truly blessed to be able to later work with and many others on giving continuity to this idea, and turning it into . (4/4)

    Show this thread
    Undo
  9. Jan 28

    One day, I came across the paper A Neural Conversational Model () by and . The paper showed sample conversations with an end-to-end learned neural network. (3/4)

    Show this thread
    Undo
  10. Jan 28

    When I was about 9 years old my father taught me how to program, and, to my delight, we built a chatbot. Initially, I couldn't stop working on it, but I no matter how many rules I wrote and how much knowledge I tried to add to its database, it still wasn't what I expected. (2/4)

    Show this thread
    Undo
  11. Retweeted
    30 Jul 2019

    (1/4) Learning ML engineering is a long slog even for legendary hackers like . IMO, the two hardest parts of ML eng are: 1) Feedback loops are measured in minutes or days in ML (compared to seconds in normal eng) 2) Errors are often silent in ML

    Show this thread
    Undo
  12. Retweeted
    19 Jun 2019

    XLNet: a new pretraining method for NLP that significantly improves upon BERT on 20 tasks (e.g., SQuAD, GLUE, RACE) arxiv: github (code + pretrained models): with Zhilin Yang, , Yiming Yang, Jaime Carbonell,

    Undo
  13. Retweeted

    An interesting trend from this year's CVPR are the numerous new papers on self-supervised learning. Andrew Zisserman gave a nice tutorial: although, there is a lot more geometry-related work as well (e.g. self-supervised depth & friends).

    Undo
  14. Retweeted

    Honored to talk w . His courses were my intro to the field & I wouldn't be here w/o his clear & inspiring teaching! I think of these, the courses, and the scholars/fellows, as the 3 essential steps I've taken in this wild journey

    Undo
  15. Retweeted

    Translatotron is our experimental model for direct end-to-end speech-to-speech translation, which demonstrates the potential for improved translation efficiency, fewer errors, and better handling of proper nouns. Learn all about it below!

    Undo
  16. Retweeted
    1 May 2019

    Really cool application of a differentiable approximation to nearest neighbours (as in e.g. NCA): aligning videos without any supervision.

    Undo
  17. Retweeted

    New blog post: "A Recipe for Training Neural Networks" a collection of attempted advice for training neural nets with a focus on how to structure that process over time

    Undo
  18. Retweeted
    6 Apr 2019

    The reason most (not all) methods don't add value (over baseline) when scaled is because they're "extra training data in disguise", so their benefit vanishes in the high data regime

    Undo
  19. Retweeted
    28 Mar 2019

    Very first tweet by after getting Turing Award "Thanks to my graduate students and postdocs whose work won a Turing award. Thanks to my visionary mentors Inman Harvey, David Rumelhart and Terry Sejnowski... " What a humble person! Very few of us would do the same.

    Undo
  20. Retweeted

    The toronto brain team celebrated Geoff's Turing award yesterday. We got two cakes, one said Hinton, the other said Turing, that way we could decide which was better.

    Undo

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·