Natural Language Processing Researcher, Johns Hopkins University
Joined February 2010
- Tweets 214
- Following 135
- Followers 917
- Likes 1
2 Photos and videos
Interested in diglossia, multilingual models, and dialectal adaptation? Please consider participating in our dialectal speech translation shared task at @iwslt iwslt.org/2022/dialect
1
4
Kevin Duh retweeted
7 Nov 2019
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…
13
73
540
Kevin Duh retweeted
8 Nov 2019
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… .
3
24
Kevin Duh retweeted
25 Apr 2017
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
69
171
Kevin Duh retweeted
5 Apr 2017
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…
2
205
341
Kevin Duh retweeted
13 Feb 2017
I wasn't really happy with existing LSTM computation graph visualizations. Here is my attempt.
16
129
463
Kevin Duh retweeted
17 Jan 2017
"DyNet: The Dynamic Neural Network Toolkit," Neubig et al. (lots of folks from all over, inc. @yoavgo and @nsaphra): arxiv.org/abs/1701.03980
3
32
58
Our guest post on the ACL2017 PC blog "Reject before review - we're sorry for it!" chairs-blog.acl2017.org/2017…
7
10
“50 things I learned at NIPS 2016” by @stuhlmueller blog.ought.com/nips-2016-875…
3
8
#emnlp2016 accepted papers are up: emnlp2016.net/accepted-paper…
1
30
41
Deep learning free course on Udacity - Built by Google udacity.com/course/deep-lear…
38
71
Recurrent nets reply your email for you. On Google blog: googleresearch.blogspot.se/2…
2
3
ACL-IJCNLP2015 talks are online, thanks to efforts of the local organizers and speakers: techtalks.tv/acl-ijcnlp-2015…
1
19
29
How do neural encoder-decoders help reranking in machine translation? Nice analysis by @neubig et al.: phontron.com/paper/neubig15w…
3
13
Kevin Duh retweeted
25 Aug 2015
Worth checking out new Deep Learning library for Python "CGT replicates Theano's API but has very short compile time" joschu.github.io/
2
95
152
Slides from the various speakers at the ACL Semantics for Statistical Machine Translation workshop are now available! hlt.suda.edu.cn/workshop/s2m…
3
6
Kevin Duh retweeted
3 Jul 2015
Very interesting blog post about Deep Nets (and limitations thereof) from the Bayesian perspective by @yaringal mlg.eng.cam.ac.uk/yarin/blog…
4
11
Fun visualization and artwork by Google's deep neural networks! googleresearch.blogspot.jp/2…
1
3