Marco Turchi

@Turchi_Marco

Head of the Machine Translation group at Fondazione Bruno Kessler . Mainly working on for .

Vrijeme pridruživanja: srpanj 2013.

Tweetovi

Blokirali ste korisnika/cu @Turchi_Marco

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

  1. proslijedio/la je Tweet
    27. sij

    Our pick of the week: et al. 2019 paper on "Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations". By

    Poništi
  2. proslijedio/la je Tweet
    24. sij

    We're releasing mBART, a new seq2seq multilingual pretraining system for machine translation across 25 languages. It gives significant improvements for document-level translation and low-resource languages. Read our paper to learn more:

    Poništi
  3. proslijedio/la je Tweet
    24. sij

    Paper accepted at "Supervised online diarization with sample mean loss for multi-domain data" Well done

    Poništi
  4. proslijedio/la je Tweet
    24. sij

    I've written a blog post on on mixed-effect models, a useful method for statistical analysis. It also includes as an example a study from our paper with , N. Bertoldi and .

    Poništi
  5. proslijedio/la je Tweet
    24. sij

    Do you have data for direct speech translation and want to update your model on the fly? Check out our paper "INSTANCE-BASED MODEL ADAPTATION FOR DIRECT SPEECH TRANSLATION" accepted to

    Poništi
  6. proslijedio/la je Tweet
    21. sij
    Poništi
  7. proslijedio/la je Tweet
    23. sij

    Very interesting blog post by on the lexical diversity of MT outputs, human translations and natural texts

    Poništi
  8. proslijedio/la je Tweet
    15. sij

    Lots of time before the March 6th deadline to consider submitting a paper to the translators' track at , chaired by and I. Details and the call for papers are at . Come join us in Lisbon!

    Poništi
  9. proslijedio/la je Tweet
    15. sij

    Our PRINCIPLE project is now live on Twitter. PRINCIPLE is a European Commission-funded project aimed at providing language data to improve translation quality via domain-specific Neural Machine Translation

    Poništi
  10. proslijedio/la je Tweet
    15. sij

    If you are interested in speech translation but have never heard of our multilingual corpus, I suggest you discover it from this source (friend link, it won't consume your visits in Medium) and check out our publication:

    Poništi
  11. proslijedio/la je Tweet
    8. sij

    Thrilled to announce the 2020 "offline speech translation" challenge. Cascaded and end-to-end models will be evaluated on the translation of TED talks from English into German. Info:

    Poništi
  12. proslijedio/la je Tweet
    7. sij

    Deadline approaching... PhD position in Natural Language Processing in Deep Summarization at in the context of the La Caixa InPhiNIT program for Maria de Maeztu units. Highly qualified candidates check information at

    Poništi
  13. proslijedio/la je Tweet
    7. sij

    If you know of native speakers of Italian who might be interested in taking part in our short survey on comprehension of flood warnings, please bring this to their attention. Thanks!

    Poništi
  14. proslijedio/la je Tweet
    3. sij

    We are hiring at WIPO: Fellowship in Neural Machine Translation - see link for details (deadline 8th Jan)

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

    Intelligenza artificiale, la realtà e il sogno, superando le paure Paolo Traverso, direttore del centro di ricerca ICT @ FBK è stato fra i protagonisti della settima edizione del FOCUS 2039. "I robot sono macchine, sta a noi porre limiti etici"

    Poništi
  17. proslijedio/la je Tweet
    17. pro 2019.
    Poništi
  18. proslijedio/la je Tweet
    16. pro 2019.

    Interesting keynote talk by Semy Bengio on generalization of deep networks

    Poništi
  19. proslijedio/la je Tweet

    We’re co-organizing a task on simultaneous speech translation as part of an workshop on spoken language translation. Entrants will be evaluated on real-time translation of TED talks from English into German. Learn more:

    Poništi
  20. proslijedio/la je Tweet
    16. pro 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:

    ·