Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @Eric_Wallace_
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @Eric_Wallace_
-
Prikvačeni tweet
Introducing Universal Adversarial Triggers Phrases that cause a specific model prediction when concatenated to 𝘢𝘯𝘺 input. Result - GPT-2 turns racist - SQuAD models predict "to kill american people" for 72% of "why" questions - Classifier acc 90%->1% http://ericswallace.com/triggers pic.twitter.com/a7yLZeXLdX
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Introducing the diversity & inclusion committee for
#ACL2020 -- thank you to all of these volunteers!https://acl2020.org/blog/diversity-and-inclusion/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I think both are positive changes. I'm still torn on the anonymity window, and I feel like it is not discussed enough. My colleagues send great NLP work to ICLR/ICML/NeurIPS instead of ACL/EMNLP/NAACL because of the arXiv policy.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
EMNLP CFP https://2020.emnlp.org/call-for-papers Sticky reviews: "a paper that has been rejected from another venue are invited to submit alongside their paper the previous version of the paper, the reviews and an author response" And a reproducibility list on hyperparameters, code, etc.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Signup for
#winlp2020 pre-submission workshopping is open: https://winlp.ling.washington.edu/survey/index.php/293366?lang=en … More info on this pre-submission process here: http://www.winlp.org/winlp-2020-workshop/presubmission-workshop/ … 3 weeks till the visa-friendly deadline!https://twitter.com/WiNLPWorkshop/status/1215781577931640833 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
I have written a note on the case for Bayesian deep learning: https://cims.nyu.edu/~andrewgw/caseforbdl/ …https://twitter.com/andrewgwils/status/1210354001041969152 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Maybe
@mrtz@zacharylipton@NicolasPapernot@iamtrask@openminedorg know some?Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Despite the research interest in differentially private ML, it still seems like there are few (maybe zero?) uses I can find in practice. I’ve seen non-ML applications like Google’s RAPPOR and the US Census. Are there real-world deployments of privacy preserving ML I am missing?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Excited that our work on characterizing racial bias in football commentary was covered by
@TheUndefeated! Thanks to@big_data_kane for thoroughly explaining and contextualizing our research to a non-academic audience. We're continuing with this work, so look out for more soon!https://twitter.com/big_data_kane/status/1214954543173324801 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
We had the most viewed 2019 news story at Maryland (brought down their servers, even). If you haven't watched the videos, now's your chance!https://cmns.umd.edu/news-events/features/4524?fbclid=IwAR0xoZkWWIRj3qI3pukewvrtjOJzVdHEbb1ZS3ccqvTgL0JD4QV0eIuPQvg …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
What're your favorite pre-2012 AI/NLP papers?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Also, let me clarify that if you are in production settings (not research), don’t start with BERT. Start with regular expressions, bag of words, etc., and only add complexity when you aren’t getting the satisfactory performance.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
(We had a good laugh afterwards). Crazy to see how our methods have changed in just a short time.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The state of NLP in 2019. I’m talking with an amazing undergrad who has already published multiple papers on BERT-type things. We are discussing deep into a new idea on pretraining. Me: What would TFIDF do here, as a simple place to start? Him: .... Me: .... Him: What’s TFIDF?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Dear authors, thank you for your patience with the submission system during the homestretch. We're giving everyone two extra hours to submit. Softconf has made some changes in the last 10 minutes so hopefully this does the trick!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
For those struggling to come up with a title for their ACL submission... =)https://twitter.com/nytimes/status/1197726459504316416 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Happy to announce that Matt (
@nlpmattg) and I are working on a free, Web-based AllenNLP (@ai2_allennlp) Course that provides onboarding of AllenNLP and in-depth tutorials on how to use the framework and its abstractions for various NLP tasks. Stay tuned! https://allennlp.org/Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Machine learning is a bit like cocaine in the 1880s: - been used in a weaker form for centuries - some surprisingly successful early applications led to it now being over-prescribed - beginning to understand that performance degrades after repeated use, negative feedback loops
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Eric Wallace proslijedio/la je Tweet
Prof. Marti Hearst
@Berkeley_EECS@BerkeleyISchool is hiring an NLP / IR postdoc to work on intelligent interfaces for augmented reading of scientific papers, in collaboration with@allen_ai! Apply at https://aprecruit.berkeley.edu/JPF02405Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We are really happy to win the best demo award. You can find tutorials and more information here https://allennlp.org/interpret . The tutorials likely miss some use cases, if you need help, feel free to open an issue on the AllenNLP Github and I will personally help you get set up!https://twitter.com/emnlp2020/status/1193238942310653959 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
With EMNLP closing, what are people’s biggest takeaways? A few for me: 1.) lots of people are thinking about dataset biases, artifacts, etc., although few solutions 2.) your baseline better be a pre-trained LM. 3.) model analysis, interpretability, probing, etc. are hot
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
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.