Rezultati pretraživanja
  1. 28. sij

    Introducing , a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness! Paper: Sample conversations:

    Prikaži ovu nit
  2. 31. sij

    I chatted with about the and her advice is to see a doctor sooner rather than later. I guess it's not a bad one & hope everyone is well! On the other hand, Meena is also excited about technology, especially VR!

  3. prije 2 sata
  4. prije 17 sati

    Google’s here to stay and hit the floor

  5. prije 22 sata
  6. 2. velj
  7. 1. velj

    Ingredients for a human-like open domain chatbot: 341GB conversation data, 2.6 billion parameters, 2048 TPU Cores and 30 days training time🤯

  8. 1. velj

    These are incredibly interesting to read.

  9. 30. sij

    Highly recommend watching this 8-minute video on & the paper, with details not included the blog such as SSA vs humanlikeness correlation, sample-and-rank, removing cross-turn repetition. (Blog: )

  10. 29. sij

    Google claims its new chatbot Meena is better than OpenAI's GPT-2

  11. 28. sij

    Implications from the project: 1. Perplexity might be "the" automatic metric that the field's been looking for. 2. Bots trained on large-scale social conversations & pushed hard for low perplexity will be good. 3. Safety layer is needed for respectful conversations!

    Prikaži ovu nit
  12. 28. sij

    We design a new human evaluation metric, Sensibleness & Specificity Average (SSA), which captures key elements of natural conversations. SSA is also shown to correlate with humanlikeness while being easier to measure. Human scores 86% SSA, 79%, other best chatbots 56%.

    Prikaži ovu nit
  13. 28. sij

    is based on the Evolved Transformer (ET, an improved Transformer) & trained to minimize perplexity, the uncertainty of predicting the next word in a conversation. We built a novel "shallow-deep" seq2seq architecture: 1 ET block for encoder & 13 ET blocks for decoder.

    Prikaži ovu nit

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.