Marco Guerini

@m_guerini

Natural Language Processing | Persuasive Technologies | Sentiment and Emotion Analysis | Content Virality in Social Media

marcoguerini.eu
Vrijeme pridruživanja: ožujak 2013.
285 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @m_guerini

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

  1. Prikvačeni tweet
    29. srp 2019.

    Counter Narratives are a novel way to fight using to avoid -> give a look to our paper: “CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech”

    1 reply 5 proslijeđenih tweetova 6 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    prije 20 sati

    It's not OK to claim that a system has "near-human abilities" while just releasing a few handpicked examples. We fully release "very-far-from-human abilities" systems every month. If your system is "near-human" it can certainly be shared.

    45 proslijeđenih tweetova 293 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    prije 19 sati

    If an algorithm has "mastered natural language", I would expect it to be able to do some of the things language is for -- communicating information, receiving information, acting on the world... Not merely output something that statistically sounds like language.

    18 replies 205 proslijeđenih tweetova 978 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    1. velj

    An older woman came into the bookstore today. I made a joke about a credit card reader issue and she said "these things are all programmed by twenty-five-year-old boys who don't comment their code" and somehow we ended up having a great conversation about programming and biases.

    279 replies 6.783 proslijeđena tweeta 80.575 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    2. velj

    Wow: Google's "Meena" chatbot was trained on a full TPUv3 pod (2048 TPU cores) for **30 full days** - That's more than $1,400,000 of compute time to train this chatbot model. (! 100+ petaflops of sustained compute !)

    39 replies 333 proslijeđena tweeta 925 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    1. velj

    I tell people to stop worrying about futuristic runaway smart AI, because it's stupid current AI that will kill us, this is what I mean. Someone bought a product that *literally* text-matched the word "charity" as 'good' and "vodka" as 'bad' and is making hiring choices with it.

    I had to get a background check for my job, and it turns out the report is a 300+ page pdf of every single tweet I’ve ever liked with the work “fuck” in it. Enjoy your dystopian bs! *waves*
    Prikaži ovu nit
    4.007 proslijeđenih tweetova 9.454 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    31. sij

    I sometimes wonder if I am reviewing papers produced by an algorithm which take a DL model, randomly tweaks it, checks if anything has improved, and iterates above process until it gets "lucky" with a tweak that works on the test set (but maybe nowhere else)

    10 proslijeđenih tweetova 36 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    31. sij

    Salgo su un treno per Pesaro. Nella carrozza entra un ragazzo cinese. Una tizia esclama ad alta voce:"Ecco qua, così s'ammalamo tutti". Il ragazzo prontamente risponde:"A signò, io la Cina in vita mia l'ho vista solo su Google Maps!". Applausi

    565 replies 6.692 proslijeđena tweeta 31.464 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    30. sij

    1 Person: I’m having trouble working with X. [story] Me: Have you told X what you just shared w me? Person: No, our 1-1s are tense. I’m afraid to share it. Me: Where are you holding 1-1s? Person, confused: Um, in a conference room? A thread about tense relationships at work >>

    12 replies 195 proslijeđenih tweetova 752 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    29. sij

    New blog post: Contrastive Self-Supervised Learning. Contrastive methods learn representations by encoding what makes two things similar or different. I find them very promising and go over some recent works such as DIM, CPC, AMDIM, CMC, MoCo etc.

    8 replies 99 proslijeđenih tweetova 452 korisnika označavaju da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    29. sij

    Machine learning success story: When I start an email by typing the letter S, gmail autocompletes it into "Sorry for the late reply!"

    9 replies 140 proslijeđenih tweetova 1.415 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    23. sij

    Today gave a talk at Google Research Berlin about our Transformer analysis work. Met a lot of great people and feel totally happy :) Want to know details? Here are the blog posts: The Story of Heads: , Evolution of Representations:

    90 proslijeđenih tweetova 414 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    24. sij

    is one of the most important techniques I don't often recommend PhD Thesis' - 's is exceptional. He's a brilliant writer! Check out this taxonomy / table of contents!!! 👇👇👇

    7 replies 297 proslijeđenih tweetova 1.033 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    27. sij

    La lingua batte dove il dente Vuole >> Insieme a Carlo Strapparava esploriamo la scienza della linguistica computazionale e l'arte delle connotazioni | |

    2 proslijeđena tweeta
    Poništi
  15. proslijedio/la je Tweet
    25. sij

    On my way to Lausanne to present 🚀 See you at 13:30 @ 3BC at our workshop on human mobility analysis. Slides and code 👉

    2 proslijeđena tweeta 8 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    25. sij

    Our unsupervised MT paper mentioned "Important AI & Machine Learning Trends for 2020"

    26 proslijeđenih tweetova 69 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 25. sij

    Looking back to this tweet from 2014. I do believe it is just a coincidence, nonetheless I find it quite disquieting...

    China and France are building a biosafety laboratory in Wuhan for basic research on infectious viruses, including : French ambassador
    1 korisnik označava da mu se sviđa
    Poništi
  18. proslijedio/la je Tweet
    24. sij

    Comprendere l'odio anti-musulmano online per poterlo prevenire in modo efficace. Questo è il progetto Grazie a e per la partecipazione al video

    6 replies 45 proslijeđenih tweetova 77 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 24. sij

    Final conference of : we are now presenting the platform for monitoring and countering

    24/01/2020 Conferenza finale Hatemeter presenta la piattaforma Hatemeter.
    1 korisnik označava da mu se sviđa
    Poništi
  20. proslijedio/la je Tweet
    24. sij

    24/01/2020 Conferenza finale progetto Hatemeter Prevenire e contrastare l’islamofobia e i discorsi d’odio online: la piattaforma Hatemeter

    6 proslijeđenih tweetova 4 korisnika označavaju da im se sviđa
    Poništi
  21. 24. sij

    The final conference of started. A long, exciting journey.

    1 proslijeđeni tweet 8 korisnika označava da im se sviđa
    Poništi

@m_guerini još nije objavio nijedan Tweet.

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:

    ·