Graham Neubig's guest appearances

Graham Neubig

NLP Highlights

The Thesis Review

Sebastian Ruder

Yoon Kim

Burr Settles

Jacob Andreas

Charles Sutton

Brendan O'Connor

Victor Sanh

Sam Bowman

Julian Togelius

Nathan Schneider

Matt Gardner

Chris Dyer

John Hewitt

Jay McClelland

Dan Roth

OwlTail

Graham Neubig is an Associate Professor at Carnegie Mellon University. His research focuses on language and its role in human communication, with the goal of breaking down barriers in human-human or human-machine communication through the development of NLP technologies.Graham’s PhD thesis is titled "Unsupervised Learning of Lexical Information for Language Processing Systems", which he completed in 2012 at Kyoto University. We discuss his PhD work related to the fundamental processing units that NLP systems use to process text, including non-parametric Bayesian models, segmentation, and alignment problems, and discuss how his perspective on machine translation has evolved over time.Episode notes: http://cs.nyu.edu/~welleck/episode22.htmlFollow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter, and find out more info about the show at http://cs.nyu.edu/~welleck/podcast.htmlSupport The Thesis Review at www.patreon.com/thesisreview or www.buymeacoffee.com/thesisreview

Graham Neubig is an Associate Professor at Carnegie Mellon University. His research focuses on language and its role in human communication, with the goal of breaking down barriers in human-human or human-machine communication through the development of NLP technologies. Graham’s PhD thesis is titled "Unsupervised Learning of Lexical Information for Language Processing Systems", which he completed in 2012 at Kyoto University. We discuss his PhD work related to the fundamental processing units that NLP systems use to process text, including non-parametric Bayesian models, segmentation, and alignment problems, and discuss how his perspective on machine translation has evolved over time. Episode notes: <a href="http://cs.nyu.edu/~welleck/episode22.html" rel="nofollow" target="_blank">http://cs.nyu.edu/~welleck/episode22.html</a> Follow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter, and find out more info about the show at <a href="http://cs.nyu.edu/~welleck/podcast.html" rel="nofollow" target="_blank">http://cs.nyu.edu/~welleck/podcast.html</a> Support The Thesis Review at <a href="http://www.patreon.com/thesisreview" rel="nofollow" target="_blank">www.patreon.com/thesisreview</a> or <a href="http://www.buymeacoffee.com/thesisreview" rel="nofollow" target="_blank">www.buymeacoffee.com/thesisreview</a>

[22] Graham Neubig - Unsupervised Learning of Lexical Information

ACL 2017 paper, by Yusuke Oda and others (including Graham Neubig) at Nara Institute of Science and Technology (Graham is now at Carnegie Mellon University).Graham comes on to talk to us about neural machine translation generally, and about this ACL paper in particular.  We spend the first half of the episode talking about major milestones in neural machine translation and why it is so much more effective than previous methods (spoiler: stronger language models help a lot).  We then talk about the specifics of binary code prediction, how it's related to a hierarchical or class-factored softmax, and how to make it robust to off-by-one-bit errors.Paper link: https://www.semanticscholar.org/paper/Neural-Machine-Translation-via-Binary-Code-Predict-Oda-Arthur/bbedfd0380eb2e62f1c3b61aaf484d5867e6358dAn example of the Language log posts that we discussed: http://languagelog.ldc.upenn.edu/nll/?p=33613 (there are many more).

ACL 2017 paper, by Yusuke Oda and others (including Graham Neubig) at Nara Institute of Science and Technology (Graham is now at Carnegie Mellon University). Graham comes on to talk to us about neural machine translation generally, and about this ACL paper in particular. We spend the first half of the episode talking about major milestones in neural machine translation and why it is so much more effective than previous methods (spoiler: stronger language models help a lot). We then talk about the specifics of binary code prediction, how it's related to a hierarchical or class-factored softmax, and how to make it robust to off-by-one-bit errors. Paper link: <a href="https://www.semanticscholar.org/paper/Neural-Machine-Translation-via-Binary-Code-Predict-Oda-Arthur/bbedfd0380eb2e62f1c3b61aaf484d5867e6358d" rel="nofollow" target="_blank">https://www.semanticscholar.org/paper/Neural-Machine-Translation-via-Binary-Code-Predict-Oda-Arthur/bbedfd0380eb2e62f1c3b61aaf484d5867e6358d</a> An example of the Language log posts that we discussed: <a href="http://languagelog.ldc.upenn.edu/nll/?p=33613" rel="nofollow" target="_blank">http://languagelog.ldc.upenn.edu/nll/?p=33613</a> (there are many more).

29 - Neural machine translation via binary code prediction, with Graham Neubig