Kevin Duh retweeted
🚋 All aboard the NAACL 2027 Paper Cable Car! 📄🌉
The Call for Main Conference Papers is live! Submit long or short papers to the Oct 2026 ARR cycle by Oct 12, 2026 (AoE).
🔗 2027.naacl.org/calls/main_co…
#NAACL2027 #NLP #ComputationalLinguistics
🤖 Made with AI
Kevin Duh retweeted
The Call for Workshop Proposals for NAACL 2027 is out! This is a single deadline for EACL, COLING, NAACL, ACL, and EMNLP 2027.
Submission deadline: Sep. 4, 2026
Notification of acceptance: Oct. 2, 2026
Kevin Duh retweeted
Huge congratulations to @XiangLisaLi2 on winning #emnlp2019 Best Paper! (From 2800+ submissions.) And on her delightful talk: video online.
Lisa did this work with me as a junior. First time any *ACL best paper award has gone to an undergrad project??
cs.jhu.edu/~jason/papers/#li…
Kevin Duh retweeted
Replying to @adveisner @XiangLisaLi2
And congrats to my close colleagues @percyliang (at #microsoft #semanticmachines) and Philipp Koehn (at Johns Hopkins @jhuclsp). They + co-authors won Best Paper runner-up
aclweb.org/anthology/D19-127… and Best Resource Paper
aclweb.org/anthology/D19-163… .
Kevin Duh retweeted
Large vocabs in neural MT? Try binary error correcting codes! Small models, 12x faster on CPU, easy on GPU #ACL2017 arxiv.org/abs/1704.06918
Kevin Duh retweeted
Google's TPU paper is out. 8-bit matmul processor, large on-die memory (28MB). Excited to finally read the details..
drive.google.com/file/d/0Bx4…
Kevin Duh retweeted
I wasn't really happy with existing LSTM computation graph visualizations. Here is my attempt.
Kevin Duh retweeted
"DyNet: The Dynamic Neural Network Toolkit," Neubig et al. (lots of folks from all over, inc. @yoavgo and @nsaphra): arxiv.org/abs/1701.03980
Kevin Duh retweeted
Deep learning free course on Udacity - Built by Google udacity.com/course/deep-lear…
Kevin Duh retweeted
Worth checking out new Deep Learning library for Python "CGT replicates Theano's API but has very short compile time" joschu.github.io/
Kevin Duh retweeted
Very interesting blog post about Deep Nets (and limitations thereof) from the Bayesian perspective by @yaringal mlg.eng.cam.ac.uk/yarin/blog…
Kevin Duh retweeted
A Multilingual Corpus of Automatically Extracted Relations from Wikipedia - learn more at goo.gl/f4zP2u
Kevin Duh retweeted
Nice ICLR ("the deep learning conf", LR=learning representations) review by @PaulMineiro (oblique h/t @beaucronin) machinedlearnings.com/2015/0…
Kevin Duh retweeted
Initialization of deep networks deepdish.io/2015/02/24/netwo… Summary of most important recent papers
Kevin Duh retweeted
Replying to @timoreilly
Kevin Duh retweeted
We applied Karpathy et al's caption generating code to fine art. I believe this is indeed... plus.google.com/+JordanBoydG…
Kevin Duh retweeted
Gotta understand your LSTMS in 2015! Useful study of variants. [1503.04069] LSTM: A Search Space Odyssey #dlearn arxiv.org/abs/1503.04069
Kevin Duh retweeted
IEEE Spectrum has an interview of me in which I pontificate about various topics related to AI, Facebook AI... fb.me/44qWFDqrn
Kevin Duh retweeted
Our paper "The loss surface of multilayer networks" by Anna Choromanska, Mikael Henaff, Michael Mathieu, Gérard... fb.me/2HjC6oaNP
Kevin Duh retweeted
Happy New Year, everyone. phdcomics.com/comics.php?f=1…
























