Life!     Janardhan Rao ( Jana ) Doppa
    School of EECS, Oregon State University
    Office: KEC 3119
    Voice: 1-541-602-1326
    Email: doppa [AT]
                           LATEST UPDATES
I did my PhD with the Artificial Intelligence group, where I was wisely advised by Prasad Tadepalli and Alan Fern . My general research interests are in Artificial Intelligence (AI) and Machine Learning (ML). Current focus of my work is on search-based structured prediction applied to natural language processing (NLP) and computer vision (CV) problems. I'm fortunate to work with Alan Fern on learning for search and I enjoy working with him a lot. I also work with Tom Dietterich on the Deep Reading and Learning project and the Tree of Life project. 

Quick Links:   [  Research  ]   [  Publications  ]   [  Teaching  ]   [  Awards and Honors  ]   [  Professional Service  ]   [  Reading Groups  ]   [  Personal  ]


Ph.D., Computer Scince, Oregon State University, 2014.
M.Tech., Computer Science, Indian Institute of Technology, Kanpur, India, 2006.


I like to work on fundamental machine learning problems motivated from important real-world applications.  A sample of my current and recent research projects include:
How can we  integrate two fundamental branches of Artificial Intelligence (AI), namely learning and search to solve structured prediction tasks (e.g., POS tagging, dependency parsing, co-reference resolution and semantic segmentation of images)? We are exploring the space of search-based approaches for a wide variety of problems in natural language processing and computer vision. See our JAIR2014 and JMLR2014 papers for details. [Funded by NSF]
How can we build intelligent computer systems that can achieve deep language understanding? In the Deep Reading and Learning project, we are trying to learn a high-level representation called event graphs (a form of Abstract Meaning Representation) from raw text. Towards this goal, we are working on several sub-problems: 1) Entity co-reference resolution within a document; 2) Joint entity and event co-reference resolution across documents; 3) Joint models for entity linking; 4) Dependency parsing; and 5) Learning general scripts of events. See our AAAI2014 paper on script learning, and EMNLP2014 paper on co-reference resolution. Other papers will come out very soon! [Funded by DARPA as part of the DEFT Program] How can we reconstruct phylogenetic trees? We are developing computer vision methods to discover and score phenotype characters from images of biological specimens. We are extending my work on search-based structured prediction to address some of the challenges that are specific to our biology domain. See our ICCV2013 workshop paper for some initial work on this project. [Funded by NSF] How can we learn relational world knowledge rules (e.g., Horn clauses) from natural texts to support textual inference? Natural texts are radically incomplete (writers don't mention redundant information) and systematically biased (writers mention exceptions to avoid the readers from making incorrect inferences), which makes the rule learning very hard. We solve this problem by modeling the pragmatic relationship between what rules exist and what things will be mentioned (e.g., Gricean maxims).  We worked with BBN and other researchers from CMU, University of Washington and ISI. See our NIPS2011 and ACML2011 papers for details. [Funded by DARPA as part of the Machine Reading program] How can we integrate information from multiple sources to learn better ? In the past, we worked on DARPA's Integrated learning project, where the goal was to learn a complex problem solving task from a single demonstration of the expert. We learned the cost function that the expert is minimizing while producing the demonstration by formulating it as an inverse optimization problem. Our component's name was DTLR (Decision Theoretic Learner and Reasoner). We worked with other researchers from Lockheed-Martin, ASU, RPI, UMD, UMASS, UIUC and Georgia Tech. See our TIST2012 paper for details. [Funded by DARPA]


  •  Learning Algorithms for Link Prediction based on Chance-Constraints
  • Janardhan Rao Doppa, Jun Yu, Prasad Tadepalli, and Lise Getoor
  • Proceedings of European Conference on Machine Learning (ECML-2010)
  • PDF
  •  Towards Learning Rules from Natural Texts
  • Janardhan Rao Doppa, Mohammad Nasresfahani, Mohammad S. Sorower, Thomas G. Dietterich, Xiaoli Fern, and Prasad Tadepalli
  • Proceedings of NAACL 2010 Workshop on Formalisms and Methodologies in Learning by Reading.
  • PDF
  • Chance-Constrained Programs for Link Prediction
  • Janardhan Rao Doppa, Jun Yu, Prasad Tadepalli, and Lise Getoor
  • Proceedings of NIPS 2009 Workshop on Analyzing Networks and Learning with Graphs.
  • PDF
  • An Ensemble Learning and Problem Solving Architecture for Airspace Management
  • Xiaoqin Zhang, Sung Wook Yoon, Phillip DiBona, Darren Scott Appling, Li Ding, Janardhan Rao Doppa, Derek T. Green, Jinhong K. Guo, Ugur Kuter, Geoffrey Levine, Reid MacTavish, Daniel McFarlane, James Michaelis, Hala Mostafa, Santiago Ontanon, Charles Parker, Jainarayan Radhakrishnan, Antons Rebguns, Bhavesh Shrestha, Zhexuan Song, Ethan Trewhitt, Huzaifa Zafar, Chongjie Zhang, Daniel D. Corkill, Gerald DeJong, Thomas G. Dietterich, Subbarao Kambhampati, Victor R. Lesser, Deborah L. McGuinness, Ashwin Ram, Diana F. Spears, Prasad Tadepalli, Elizabeth T. Whitaker, Weng-Keen Wong, James A. Hendler, Martin O. Hofmann, and Kenneth R. Whitebread
  • Proceedings of AAAI Conference on Innovative Applications of Artificial Intelligence (IAAI-2009)
  • PDF

  • Teaching

    I was Instructor for the following courses:

    I was Teaching Assistant for the following courses:

    Professional Service

        Program Committee Member:

        Departmental Service:

        Volunteer Service: 

    Machine Learning Reading Group (MLRG)

    Over the years, I organized and led several reading groups on a wide variety of topics. Some of them include:

    Awards and Honors


    I'm passionate about cricket. Playing cricket helps me remain sane amidst the hectic research life. I try to play in the nearby cricket leagues during the summers. I played for OSU Cricket club in 2007, 2008 and 2009. Our team Chak De Oregon won the 2009 NWCL cricket championship.  In 2010, I played for Chak De Oregon in NWCL (Div I) and for Portland club in OCL. We won the 2010 OCL T20 championship. In 2011, I played for only Portland club in OCL as part of the budget cut on cricket. After 2011 season I became very busy and could not justify my time spent on cricket, so I temporarily picked Badminton and Racquetball. I maintain my cricket scores here

    I like to cook, but I don't like to spend too much time on it. So I follow an engineering methodology for cooking, which provides a good trade off between  preparation time and quality of the food! Does this remind you of my research work on trading off computation time and quality of the predictions? :)