Marcello Federico

@marcfede

Researcher in human language technologies

Palo Alto, CA
Vrijeme pridruživanja: studeni 2010.

Tweetovi

Blokirali ste korisnika/cu @marcfede

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

  1. proslijedio/la je Tweet
    14. sij

    Participants to the shared task on simultaneous speech translation () may have access to a limited amount of cloud credits! Apply here:

    Poništi
  2. proslijedio/la je Tweet
    3. velj

    Interested in translation, and how to handle disfluent conversational speech with current models? Check out our Conversational Speech Translation task! We have a constrained track and tracks for speech and text translation to be approachable to all! 🙂

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    30. pro 2019.

    IWSLT 2020 will be held as an event on July 9-10, 2020, in Seattle, WA, USA. Watch this space for updates related specifically to .

    Poništi
  4. proslijedio/la je Tweet
    31. sij

    We are delighted to inform the world that and have just submitted their PhD thesis! 👏👍 Super proud of you!

    Poništi
  5. 30. pro 2019.

    Website with Images of people created by generative adversarial networks: - Actually people alike the pictures could exist, no? :-)

    Poništi
  6. proslijedio/la je Tweet

    I think we tend to overestimate the importance of reciprocity -- a transactional mindset -- and underestimate the power of kindness. Even the smallest acts of kindness can change lives. None of the most important things in life are transactional.

    Prikaži ovu nit
    Poništi
  7. 30. stu 2019.

    It was my pleasure and honor to be back at after 13 years and meet its students and faculty. Thank you everyone for the kind hospitality and great discussions.

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

    We're delighted to announce that Marcello Federico will be a keynote speakers at NeTTT and a lecturer at the NMT summer school! Marcello's the Principal Applied Scientist at Amazon AI, leading a research project on speech translation.

    Poništi
  9. proslijedio/la je Tweet
    25. lis 2019.

    "Robust Neural Machine Translation for Clean and Noisy Speech Transcripts", done during my internship has been accepted to IWSLT and available @ . Is fine-tuning MT systems on ASR output sufficient for speech translation?

    Poništi
  10. 16. lis 2019.
    Prikaži ovu nit
    Poništi
  11. 16. lis 2019.
    Prikaži ovu nit
    Poništi
  12. 30. ruj 2019.

    Congrats to for her successful PhD defense!

    Poništi
  13. 17. ruj 2019.
    Poništi
  14. 30. srp 2019.

    I attended the talk and agree with . I found it rather disrespectful w.r.t. the interpreters, making believe they are inadequate for this task. Don't think this is the way to promote AI. Btw talk "forgot" to mention that Alex Waibel's team pioneered this almost 10y ago!

    Poništi
  15. 30. srp 2019.

    A seesaw across Trump's wall to let Mexican and US children play together! Just wonderful!

    Poništi
  16. 30. srp 2019.

    Georgiana presenting our work on training neural mt to apply terminology constraints @

    Poništi
  17. 28. srp 2019.

    Almost in Florence for !

    Poništi
  18. proslijedio/la je Tweet
    27. srp 2019.

    Yoshua Bengio @ discussing the elephant in the room... Couldn't summarize it better myself. Full round of applause followed.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    23. srp 2019.

    I'm honored to be part of this amazing list of speakers! Looking forward to September, !

    Poništi
  20. proslijedio/la je Tweet
    4. srp 2019.

    MuST-C: a large & expanding made of triplets (🗣️, EN 📖, translated 📖) extracted from TED talks. Can be used for training direct & contains 8 language directions, with up to 504h of translated 🗣️ per language. 👍

    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:

    ·