Stanford NLP Group

@stanfordnlp

Computational Linguistics—Natural Language—Machine Learning—Deep Learning—Technology from Silicon Valley. (, , & )

Stanford, CA, USA
Vrijeme pridruživanja: veljača 2010.

Tweetovi

Blokirali ste korisnika/cu @stanfordnlp

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

  1. Thread 👇 We’ve also had a difficult time with CuDNN as soon as you want to go beyond a basic LSTM and grab cell states, do -style dropout, etc. Maybe now that has an team, things might get better?

    Poništi
  2. proslijedio/la je Tweet
    2. velj

    So Google featured me in one of their blogs!! ...Not in the blog for computer scientists tho, that would be silly. In the blog for FEMALE computer scientists. We're like computer scientists, but with cooties.

    Poništi
  3. proslijedio/la je Tweet
    2. velj

    Changes to my extension spacy_conll: expanded docs on how to use w/ models by using spacy-stanfordnlp to get "real" UD results. Added option for custom tagset mapping in case you have your own tagset mapping.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    2. velj

    Python source code for 2019 nCoV realtime Tracking App Scapy + influxdb + grafana + NLTK + Stanford CoreNLP + Elastic Search with Docker Container

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    1. velj

    Started "auditing" this Stanford NLP With Deep Learning course. Interest is piqued for sure.

    Poništi
  6. proslijedio/la je Tweet
    31. sij

    Transformers 2.4.0 is out 🤗 - Training transformers from scratch is now supported - New models, including *FlauBERT*, Dutch BERT, *UmBERTo* - Revamped documentation - First multi-modal model, MMBT from , text & images Bye bye Python 2 🙃

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    1. velj

    Update benchmark score Add parse info to output Fix regression test via stanfordnlp/CoreNLP

    Poništi
  8. proslijedio/la je Tweet
    31. sij
    Poništi
  9. proslijedio/la je Tweet
    31. sij

    It can be challenging for an AI to create humor as it takes more creativity and relational reasoning to create witty context. Check out how Stanford scientists are exploring the concept with a pun generator. :

    Poništi
  10. proslijedio/la je Tweet
    30. sij

    Net of the Week: GloVe 100-dimensional word vectors trained on Tweets: . Thank you Jeffrey Pennington, , & at for creating this model .

    Poništi
  11. proslijedio/la je Tweet
    29. sij
    Poništi
  12. proslijedio/la je Tweet
    29. sij

    Stanford Lexical Parser is giving astonishing results with Arabic texts.

    Poništi
  13. proslijedio/la je Tweet
    29. sij
    Poništi
  14. proslijedio/la je Tweet
    29. sij

    Seminar tomorrow: on "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias" Please join us!

    Poništi
  15. 29. sij

    And former ⁦⁩ PhD Student Angel Chang now at Simon Fraser is number 3 in this group of 10 ⁦⁩ videos on people in AI

    Poništi
  16. 29. sij

    Here’s an article in ⁦⁩ about recent ⁦ postdoc and ⁦⁩ PhD student ⁦ touching on human language, , and deep learning

    Poništi
  17. proslijedio/la je Tweet
    Odgovor korisnicima

    We tie 6 strongly simplified RNN layers in a CPU-optimized transformer hybrid with very little quality loss. Been doing that for two years now in production, wrote about it only now :)

    Poništi
  18. proslijedio/la je Tweet
    28. sij

    "Virtual assistants are like the new browsers." - , prof. of computer science. Listen to her talk with HAI associate director on one of the of most downloaded episodes of podcast "The Future of Everything."

    Poništi
  19. proslijedio/la je Tweet

    seq2seq still delivers : ) Incredible how far we've gotten in ~5 years of progress in neural conversational models, with relatively small changes. More exciting is that there's still LOTS to be done! Paper: Blog:

    Poništi
  20. proslijedio/la je Tweet
    28. sij

    The first CodeX lunchtime series of 2020 will be next Tuesday (February 4th) at 12:45PM in SLS Room 190 (or remotely). The talk will feature SLS Assistant Professor discussing how NLP can be applied to study gaps in commercial contracts.

    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:

    ·