Rico Sennrich

@RicoSennrich

SNSF Professor at University of Zurich / Lecturer at University of Edinburgh.

Vrijeme pridruživanja: prosinac 2016.

Tweetovi

Blokirali ste korisnika/cu @RicoSennrich

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

  1. proslijedio/la je Tweet
    5. velj

    very proud & superexcited to be awarded with the DocCH grant by which will provide full funding for my project on for low-resource language variations at 🤩

    Poništi
  2. proslijedio/la je Tweet
    29. sij

    Happy to receive Facebook PhD Fellowship! I feel extremely lucky to be supervised by and , who always support me, and to be part of such great groups as and

    Poništi
  3. proslijedio/la je Tweet
    22. sij

    🎤 Live broadcast starts in 15 minutes! will be presenting "Evolution of Representations in the Transformer," from the Rasa office in Berlin. Tune in to the livestream:

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

    I am so happy to share that our paper 'A Latent Morphology Model for Open-Vocabulary Neural Machine Translation' with and is accepted to ICLR as a spotlight presentation! Read the paper here (camera-ready is coming soon):

    Poništi
  5. proslijedio/la je Tweet
    9. pro 2019.

    98: tells us about the relative importance of attention heads in multi-headed attention and evolution of token representations in transformers. and I had fun chatting with Lena for this episode.

    Poništi
  6. proslijedio/la je Tweet
    26. stu 2019.

    The School of Informatics at Edinburgh is hiring a Lecturer/Senior Lecturer/Reader in Natural Language Processing (assistant/associate prof in US parlance):

    Poništi
  7. proslijedio/la je Tweet
    26. stu 2019.

    Congratulations to Mirella Lapata , who has just been elected a Fellow of the Association for Computational Linguistics (ACL). Well deserved!

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

    2nd day of : Evolution of Representations in the Transformer! 16:30-18:00, hall 2A, poster P43 (another paper with my research parents and )

    Poništi
  9. proslijedio/la je Tweet
    5. stu 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    First day of : had a lot of fun explaining how to do context-aware NMT without document-level parallel data and, what is more surprising, why it even works :) (the paper with my research parents and )

    Poništi
  10. proslijedio/la je Tweet
    3. stu 2019.

    Mentioned 's NMT paper, 2 other papers presented on Tue: on multi-pass decoding for semantic role labeling (w/Shay Cohen) on training deep and fast Transformers (w/ )

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

    Tue at 13.30, Hall 2A: will show how a document-level MT model can be trained *without* any document-level parallel data + look into which phenomena are hard to capture with monolingual data alone (w/)

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

    If at EMNLP, come talk to me at the poster for this paper at 16.30 on Wednesday, Hall 2A :) (paper with and )

    Poništi
  13. 30. lis 2019.
    Poništi
  14. proslijedio/la je Tweet
    30. lis 2019.

    [1/3] BPE-dropout: our new paper by Ivan Provilkov and Dmitrii Emelianenko! In training, we corrupt segmentation procedure of BPE to produce different segmentations of the same word. In inference, we use standard BPE and outperform BPE and sentencepiece.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    23. lis 2019.

    Last Thursday has defended his thesis : « Unsupervised Machine Translation » Supervised by and Marc Ranzato Congratulations !!!

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    15. lis 2019.

    ELITR @metaforum2019 in Brussels😀Automatic Speech Recognition, Spoken Language Translation, Machine Translation, Automatic Minuting = For Barrier-Free Communication within Europe! #horizon2020#euprojects#metaforum#metaforum2019#metaforumbrussels

    , , i još njih 4
    Poništi
  17. proslijedio/la je Tweet

    Congratulations to our MA student Isabel Meraner, who won the -Nachwuchspreis for the best MA thesis! With Isabel's win, the prize by goes to a student from for the second time in a row!

    Poništi
  18. proslijedio/la je Tweet
    11. lis 2019.

    For the last talk of the day, sheds light on what Transformers learn, using pruning techniques among others.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    11. lis 2019.

    Now asks "What Do Transformers Learn in NLP?" and offers "Recent Insights from Model Analysis" at

    Prikaži ovu nit
    Poništi
  20. 30. ruj 2019.
    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:

    ·