John Hewitt

I graduated with a degree in Computer Science from the University of Pennsylvania in May 2018!

I start my PhD in Natural Language Processing at Stanford University in the fall.

I ask questions about structured prediction tasks – like machine translation or morphological prediction – that help us come to a better understanding of where linguistic theory and external information can improve our modeling of human language.

As an undergraduate, I worked in the lab of Chris Callison-Burch, who was an excellent advisor. We released the Massively Multilingual Image Dataset at ACL2018, for use in multimodal multilingual NLP. You can find the paper here; the website is currently under construction.

Feel free to look me up on Google Scholar or Twitter, or take my CV.


  • [Summer 2018] I’m working with the Amazon AI Lex team on natural language understanding.
  • [Summer 2018] Long paper on derivational morphology with Dan Deutsch and Dan Roth accepted to ACL!
  • [Summer 2018] Long paper on learning translations via images with Daphne Ippolito, Brendan Callahan, Reno Kriz, Derry Wijaya, and Chris Callison-Burch accepted to ACL!
  • Publications
  • Blog
  • Projects
  • About


    I’m a computer nerd and a language nerd. I like making coffee, reading research papers, and programming computers.

    I highly suggest Arch Linux for its configurability and the educational experience it provides..


    Take my school email johnhew@stanford

    Or take my Apache email johnhew@apache

    Either way, I’m expecting that you are able to predict the TLD of the above emails and fill them.

Join My Newsletter

Sign up to receive weekly updates.