Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
Blokirali ste korisnika/cu @tuvuumass
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @tuvuumass
-
Prikvačeni tweet
Excited to share our
#acl2019nlp paper (https://arxiv.org/abs/1906.03656 ) which improves paragraph classification by pretraining the encoder on unlabeled data using our sentence content objective. Work done with my advisor@MohitIyyer. Code: https://github.com/tuvuumass/SCoPE . Summary below [1/5]Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Break it down! Introducing the "Break"
#NLU benchmark for testing the ability of models to break down a question into required steps for computing the answer. Accepted for#TACL2020. Learn more about Break in this post by Tomer Wolfson on the AI2 Blog:https://medium.com/ai2-blog/break-mapping-natural-language-questions-to-their-meaning-representation-31bb753701d6 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Humans learn from curriculum since birth. We can learn complicated math problems because we have accumulated enough prior knowledge. This could be true for training a ML/RL model as well. Let see how curriculum can help an RL agent learn:https://lilianweng.github.io/lil-log/2020/01/29/curriculum-for-reinforcement-learning.html …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
This week's LTI Colloquium is
@MohitIyyer from@UMassAmherst on "Towards Story Generation"! Come learn how to train models that can efficiently generate more coherent and stylistically consistent stories: https://lti.cs.cmu.edu/lti-colloquium pic.twitter.com/rDcJdguFeR
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
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.https://ankeshanand.com/blog/2020/01/26/contrative-self-supervised-learning.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
New paper: Towards a Human-like Open-Domain Chatbot. Key takeaways: 1. "Perplexity is all a chatbot needs" ;) 2. We're getting closer to a high-quality chatbot that can chat about anything Paper: https://arxiv.org/abs/2001.09977 Blog: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html …pic.twitter.com/5SOBa58qx3
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Introducing
#MeenaBot, a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness! Paper: https://arxiv.org/abs/2001.09977 Sample conversations: https://github.com/google-research/google-research/tree/master/meena … https://twitter.com/GoogleAI/status/1222230622355087360 …pic.twitter.com/3xNSV4r4uB
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
[1/2] Excited to present SMART: Semi-Autoregressive Training for Conditional Masked Language Models. SMART closes the performance gap between semi- and fully-autoregressive MT models, while retaining the benefits of fast parallel decoding. With
@omerlevy_@LukeZettlemoyerPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
We ( Ananth,
@AlonTalmor,@sameer_ ,@nlpmattg) , are pleased to announce the release of ORB, an Open Reading Benchmark. This is an evaluation server that tests a single model on a variety of reading comprehension datasets (SQuAD, DROP, Quoref, ...). https://leaderboard.allenai.org/orbPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu 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 -
Tu Vu proslijedio/la je Tweet
We present our new year special: “oLMpics - On what Language Model pre-training captures״, http://arxiv.org/abs/1912.13283 , Exploring what symbolic reasoning skills are learned from an LM objective. We introduce 8 oLMpic games and controls for disentangling pre-training from fine-tuning.pic.twitter.com/ECQ7ZpcKlg
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Our work on nearest neighbor language models has been accepted to
#ICLR2020 Woohoo!! Code coming in the new year!https://twitter.com/ukhndlwl/status/1191188235629711360 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Finally can reveal our
#ICLR2020 paper on ELECTRA, much more efficient than existing pretraining, state-of-the-art results; more importantly, trainable with one GPU! Key idea is to have losses on all tokens. Joint work@clark_kev ,@chrmanning,@quocleix. https://openreview.net/forum?id=r1xMH1BtvB … https://twitter.com/colinraffel/status/1197064951174533120 …pic.twitter.com/2MdLJRMmvz
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Our MixTape is 3.5-10.5x faster than Mixture of Softmaxes /w SOTA results in language modeling & translation. Key is to do gating in the logit space but with vectors instead of scalars (+sigmoid tree decomposition & gate sharing for efficiency). /w Zhilin, Russ, Quoc
#NeurIPS2019 https://twitter.com/rsalakhu/status/1205128890584309760 …pic.twitter.com/m4QAQKglJH
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Ever wanted to combine the NLU superpowers of BERT with the generation superpowers of GPT-2? It's now possible in transformers thanks to
@remilouf! https://medium.com/huggingface/encoder-decoders-in-transformers-a-hybrid-pre-trained-architecture-for-seq2seq-af4d7bf14bb8 …pic.twitter.com/xlsMAi7ipY
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Transformers v2.2 is out, with *4* new models and seq2seq capabilities! ALBERT is released alongside CamemBERT, implemented by the authors, DistilRoBERTa (twice as fast as RoBERTa-base!) and GPT-2 XL! Encoder-decoder with
Model2Model
Available on https://github.com/huggingface/transformers/releases/tag/v2.2.0 …pic.twitter.com/r6M39jYPHf
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
New blog post! Lots of BERT compression papers lately... I put them all in one place and did a brief taxonomy.http://mitchgordon.me/machine/learning/2019/11/18/all-the-ways-to-compress-BERT.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Another view of Noisy Student: semi-supervised learning is great even when labeled data is plentiful! 130M unlabeled images yields 1% gain over previous ImageNet SOTA that uses 3.5B weakly labeled examples! joint work /w
@QizheXie, Ed Hovy,@quocleix https://paperswithcode.com/sota/image-classification-on-imagenet …https://twitter.com/quocleix/status/1194334947156193280 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Want to improve accuracy and robustness of your model? Use unlabeled data! Our new work uses self-training on unlabeled data to achieve 87.4% top-1 on ImageNet, 1% better than SOTA. Huge gains are seen on harder benchmarks (ImageNet-A, C and P). Link: https://arxiv.org/abs/1911.04252 pic.twitter.com/0umSnX7wui
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Excited to host
@MohitIyyer this Thursday@NYUDataScience for a talk on "Rethinking Transformers for machine translation and story generation": https://cds.nyu.edu/text-data-speaker-series/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tu Vu proslijedio/la je Tweet
Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data while learning in a supervised learning manner. My latest post covers many interesting ideas of self-supervised learning tasks on images, videos & control problems:https://lilianweng.github.io/lil-log/2019/11/10/self-supervised-learning.html …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.