Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @srush_nlp
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @srush_nlp
-
Sasha Rush proslijedio/la je Tweet
Looking to hire a developer/intern in the NYC area. Here is a quick (approximate) description. Please apply here: https://forms.gle/DnVzggPJ1xoUH1wr9 … DM (or email) me with any questions. Please RT to spread the word!
pic.twitter.com/YAyt35hWlr
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My group is looking for PhD students this year. We're researching text generation, struct. prediction, generative NLP / vis, and compression. Also excited to hear what interests you. I'm at Cornell Tech in NYC (student's view below). If you are interested, apply to Cornell CS.pic.twitter.com/Dmn0ULGcQI
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dear NLP, \aclfinalcopy % Uncomment this line to make Overleaf work


Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
One more alignment plot. These require some of the new sparse matrices calculations to scale. (otherwise they push the limits of pytorch internals)pic.twitter.com/dk4e1SJ9ry
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
GPUs are still wild to me. Let's just casually parse a 1500 word sentence in python/colab in half a second.pic.twitter.com/J3csK7kr4v
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
PyTorch-Struct (v0.4 https://github.com/harvardnlp/pytorch-struct …). Library `genbmm` for speed/memory improvements. New CUDA kernels for log-space matmul and banded sparse matrices (https://github.com/harvardnlp/genbmm/blob/master/notebooks/Sparse.ipynb …)pic.twitter.com/5ty4kcds5f
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Looking for an intern/programmer for the spring to work on some projects in the NYC area. Find me at
#nds2019 or send me an email.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa interned with us last summer and did incredible work, (and taught us all a lot about NLP). So excited to see this. Not that this needs saying, but you should probably admit her to grad school....https://twitter.com/adveisner/status/1192588965884284928 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sasha Rush proslijedio/la je Tweet
Summarization is one of the most important & least solved tasks in
#NLProc Problem with all#DeepLearning models: they are not optimized for factual correctness We introduce a new task, dataset and model. Work by@iam_wkr@BMarcusMcCann@CaimingXiong Paper https://arxiv.org/abs/1910.12840 pic.twitter.com/pumDBw4RbO
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sasha Rush proslijedio/la je Tweet
What can we learn from a set of 3000 birth stories?
@dmimno,@karen_ec_levy, and I explore an online community's shared understanding of childbirth through a computational analysis of narrative patterns and power dynamics.#CSCW2019pic.twitter.com/ABhlcVnVc8
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sasha Rush proslijedio/la je Tweet
New paper by salesforce on learning a model-based fact checker for Abstractive Summarization. Definitely a much needed evaluation approach, let's hope that these kinds of metrics will become a new standard. Link: https://arxiv.org/abs/1910.12840
#NLProcHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Doc link fixed: http://nlp.seas.harvard.edu/pytorch-struct/model.html … Also trying to add a bibliography as I go: http://nlp.seas.harvard.edu/pytorch-struct/refs.html …pic.twitter.com/5F0IJ0047c
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
PyTorch-Struct (v0.3 https://github.com/harvardnlp/pytorch-struct …). New features: autoregressive models / beam search, sparse-max dp, alignment/dtw, parallel semi-markov, k-max, pretty docs (http://harvardnlp.github.io/pytorch-struct ) Fun example: gradients of time-warping crf under different semirings.pic.twitter.com/HB3umU5jgd
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Anyone have a list of the accepted NLP workshops? Just curious.
@aclmeetingHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sasha Rush proslijedio/la je Tweet
Our ACL tutorial on interpretability got accepted! Please help us crowdsourced potential topics you'd like to see!https://twitter.com/boknilev/status/1188070673303982081 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New analysis tool from folks at MIT/IBM and Harvard NLP.https://twitter.com/Ben_Hoov/status/1183823783754371076 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
More really useful PyTorch goodies.https://twitter.com/egrefen/status/1181181448306475010 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
PyTorch-Struct (v0.2 https://github.com/harvardnlp/pytorch-struct …). CRF distributions API, documentation, parsing datasets, new structured models, Tree/Span-LSTM, DGL adapters, and perf. Fun example: RL for learning tree network over math (ListOps)pic.twitter.com/QQ5Whby653
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Here's the multiheaded tensor tutorial for Named Tensor https://pytorch.org/tutorials/intermediate/named_tensor_tutorial.html … (Also follow Richard Zou https://github.com/zou3519 who spec'd / implemented this.)
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Not sure if there are docs yet, but they put a lot of thought into it that improves on the original version.
Prikaži ovu nitHvala. 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.