Kevin Duh

Natural Language Processing Researcher, Johns Hopkins University

[Kevin Duh @kevinduh]

Interested in diglossia, multilingual models, and dialectal adaptation? Please consider participating in our dialectal speech translation shared task at @iwslt https://t.co/jDPSOfb7Sh

[Jason Eisner @adveisner]

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??
https://t.co/4NbyXlVyyN

[Jason Eisner @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
https://t.co/12HwTREgqs and Best Resource Paper
https://t.co/SFn9lrY9J8 .

[Graham Neubig @gneubig]

Large vocabs in neural MT? Try binary error correcting codes! Small models, 12x faster on CPU, easy on GPU #ACL2017 https://t.co/Iv4yKxYL4d

[Soumith Chintala @soumithchintala]

Google's TPU paper is out. 8-bit matmul processor, large on-die memory (28MB). Excited to finally read the details..
https://t.co/qC6FBAskbg

[Tim Rocktäschel @_rockt]

I wasn't really happy with existing LSTM computation graph visualizations. Here is my attempt.

[Miles Brundage @Miles_Brundage]

"DyNet: The Dynamic Neural Network Toolkit," Neubig et al. (lots of folks from all over, inc. @yoavgo and @nsaphra): https://t.co/4dxFFQcHjM

[Kevin Duh @kevinduh]

Our guest post on the ACL2017 PC blog "Reject before review - we're sorry for it!" https://t.co/gxcT4sYw77

[Kevin Duh @kevinduh]

“50 things I learned at NIPS 2016” by @stuhlmueller https://t.co/cj6fbmHkDO

[Kevin Duh @kevinduh]

@daiquocng overall ~25%.

[Kevin Duh @kevinduh]

#emnlp2016 accepted papers are up: https://t.co/HRCszzkoVC

[jtoy @jtoy]

Deep learning free course on Udacity - Built by Google https://t.co/jZuOgotNS1

[Kevin Duh @kevinduh]

@zehavoc @haldaume3 Thanks. Are you referring to Latin Amer. Spanish Discussion Forum Treebank? https://t.co/dxC7dL9BJC

[Kevin Duh @kevinduh]

#NLP question: Are there any efforts on translating the English Web Treebank (LDC2012T13), e.g. into Russian, Spanish, Chinese?

[Kevin Duh @kevinduh]

@AlexCapecelatro Sorry, I just noticed your message. No I wasn't at NIPS this year.

[Kevin Duh @kevinduh]

Recurrent nets reply your email for you. On Google blog: https://t.co/F6vHhrmGCF

[Kevin Duh @kevinduh]

ACL-IJCNLP2015 talks are online, thanks to efforts of the local organizers and speakers: http://t.co/vlXdtcF25J

[Kevin Duh @kevinduh]

How do neural encoder-decoders help reranking in machine translation? Nice analysis by @neubig et al.: http://t.co/1JnDgIjCFx

[Andrej Karpathy @karpathy]

Worth checking out new Deep Learning library for Python "CGT replicates Theano's API but has very short compile time" http://t.co/x2gY0MVLFT