What I do

I'm a fourth year PhD student in the Language Technologies Institute, in the School of Computer Science, at Carnegie Mellon University (though my advisor moved to the University of Washington, so I live in Seattle). I'm interested in statistical machine learning. In the past, I've worked on natural language processing and vision. Projects that have interested me included generating descriptions of images, semantic parsing, temporal grounding of events, question answering with neural networks, and hyperparameter optimization. I've been very lucky to work with some fantastic people. I currently am advised by Noah Smith. As an undergrad at the University of Washington my honors thesis was advised by Luke Zettlemoyer.

During the summer of 2011, I was selected to participate in the John's Hopkins summer workshop as an undergrad, where I worked with a host of fantastic people (and got a great sweatshirt). I was on the vision and language team; you can see the website for our project here.

In the summer and fall of 2015 I interned at Facebook AI Research in NYC, where I built the Movie Dialog dataset and the MovieQA dataset. Slate.com wrote an article that covered some of my work!

See below for a list of my publications.



Publications

  • Random Search for Hyperparameters using Determinantal Point Processes
    Jesse Dodge, Catrìona Anderson, Noah A. Smith
    Arxiv, 2017

  • Key-Value Memory Networks for Directly Reading Documents
    Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, Jason Weston,
    Empirical Methods on Natural Language Processing (EMNLP), 2016

  • Evaluating Prerequisite Qualities for Learning End-to-end Dialog Systems [poster]
    Jesse Dodge*, Andreea Gane*, Xiang Zhang*, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, Jason Weston,
    International Conference on Learning Representations (ICLR), 2016
    * denotes equal contribution

  • Retrofitting Word Vectors to Semantic Lexicons
     Manaal Faruqui, Jesse Dodge, Sujay Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith
    North American Chapter of the Association for Computational Linguistics (NAACL), 2015
    Won best student paper

  • Large scale retrieval and generation of image descriptions
    Vicente Ordonez, Xufeng Han, Polina Kuznetsova, Girish Kulkarni, Margaret Mitchell, Kota Yamaguchi, Karl Sratos, Amit Goyal, Jesse Dodge, Alysssa Mensch, Hal Daumé III Alexander C. Berg, Yejin Choi, Tamara L. Berg, International Journal of Computer Vision, 2015.

  • CMU: Arc-Factored, Discriminative Semantic Dependency Parsing
    Sam Thomson, Brendan O'Connor, Jeffrey Flanigan, David Bamman, Jesse Dodge, Swabha Swayamdipta, Nathan Schneider, Chris Dyer, Noah A. Smith
    International Workshop on Semantic Evaluations (SemEval), 2014.

  • Context-dependent Semantic Parsing for Time Expressions [demo] [code] [tool]
    Kenton Lee, Yoav Artzi, Jesse Dodge, Luke Zettlemoyer
    Association for Computational Linguistic (ACL), 2014.

  • Midge: Generating Image Descriptions From Computer Vision Detections
    Margaret Mitchell, Jesse Dodge, Amit Goyal, Kota Yamaguchi, Karl Sratos, Xufeng Han, Alysssa Mensch, Alexander C. Berg, Tamara L. Berg, Hal Daumé III
    European Chapter of the Association for computational Linguistics (EACL), 2012.

  • Understanding and Predicting Importance in Images
    Alexander C. Berg, Tamara L Berg Hal Daumé III, Jesse Dodge, Amit Goyal, Xufeng Han, Alyssa Mensch, Margaret Mitchell, Aneesh Sood, Karl Stratos, Kota Yamaguchi,
    Computer Vision and Pattern Recognition (CVPR), 2012.

  • Detecting Visual Text
    Jesse Dodge, Amit Goyal, Xufeng Han, Alyssa Mensch, Margaret Mitchell, Karl Stratos, Kota Yamaguchi, Yejin Choi, Hal Daumé III, Alexander C. Berg, Tamara L. Berg
    North American Chapter of the Association for Computational Linguistics (NAACL), 2012.



    Presentations, posters, and other work

  • Presentation: Context-dependent Semantic Parsing for Time Expressions
    Kenton Lee, Yoav Artzi, Jesse Dodge, Luke Zettlemoyer
    Cambridge NLP Seminar, Cambridge University, UK

  • Poster: Graph-based Algorithms for Semantic Parsing
    Jeffrey Flanigan, Sam Thomson, David Bamman, Jesse Dodge, Manaal Faruqui, Brendan O'Connor, Nathan Schneider, Swabha Swayamdipta, Chris Dyer, Noah A. Smith
    Workshop on Semantic Parsing at Association for Computational Linguistics (ACL), 2014

  • An Exploration of How to Learn from Visually Descriptive Text
    Alexander C. Berg, Tamara L. Berg, Hal Daumé III, Jesse Dodge, Amit Goyal, Xufeng Han, Alyssa Mensch, Margaret Mitchell, Karl Stratos, Kota Yamaguchi
    JHU-CLSP Summer Workshop Whitepaper, 2011.

  • Pikachu, Domosaur, and other Monolexical Languages
    Sarah Allen, Jesse Dodge, Domosaur
    Winner of the prestigious Award Award Award Award Award Award Award
    SIGBOVK 2014