Mahesh Joshi



  • UPDATE: As of May 2013, I have graduated from the PhD program at Carnegie Mellon. I will soon be joining eBay Inc. as an Applied Researcher.
  • PhD student @ LTI, SCS, CMU
  • Advised by Prof. Carolyn Rosé and Prof. William Cohen
  • Interested in multi-domain learning, sentiment analysis, conversation analysis (in general: machine learning for natural language processing)
  • Has worked on word sense disambiguation and abbreviation expansion in the medical domain, with Prof. Ted Pedersen and Prof. Rich Maclin

    Publications

    2013

  • Mahesh Joshi, Mark Dredze, William W. Cohen and Carolyn P. Rosé. What's in a Domain? Multi-Domain Learning for Multi-Attribute Data. To appear in Proceedings of NAACL-HLT 2013, Short Papers Track.
         [paper]
  • 2012

  • Mahesh Joshi, Mark Dredze, William W. Cohen and Carolyn P. Rosé. Multi-Domain Learning: When Do Domains Matter? Proceedings of EMNLP-CoNLL 2012.
         [paper]
  • 2010

  • Mahesh Joshi, Dipanjan Das, Kevin Gimpel and Noah Smith. Movie Reviews and Revenues: An Experiment in Text Regression. Proceedings of NAACL-HLT 2010, Short Papers Track.
         [paper]      [poster]      [data]
  • 2009

  • Mahesh Joshi and Carolyn Rosé. Generalizing Dependency Features for Opinion Mining. In Proceedings of ACL-IJCNLP 2009, Short Papers Track.
         [paper]      [slides]      [data]
  • Shilpa Arora, Mahesh Joshi and Carolyn Rosé. Identifying Types of Claims in Online Customer Reviews. In Proceedings of NAACL-HLT 2009, Short Papers Track.
         [paper]      [data]
  • 2008

  • Mahesh Joshi, Yi-Chia Wang, John Wilkerson and Carolyn Rosé. A Needs Analysis for Instructional Support in LegSim. In Proceedings of the 2008 International Conference of the Learning Sciences (ICLS 2008), Poster Presentation.
         [paper]      [poster]
  • Yi-Chia Wang, Mahesh Joshi, Carolyn Rosé and William Cohen. Recovering Implicit Thread Structure in Newsgroup Style Conversations. In Proceedings of the 2nd International Conference on Weblogs and Social Media (ICWSM 2008).
         [paper]
  • Moonyoung Kang, Sourish Chaudhuri, Mahesh Joshi and Carolyn Rosé. SIDE: The Summarization Integrated Development Environment. In Proceedings of ACL-HLT 2008, Demo Abstracts.
         [paper]
  • 2007

  • Mahesh Joshi and Carolyn Rosé. Using Transactivity in Conversation for Summarization of Educational Dialog. In Proceedings of the SLaTE Workshop on Speech and Language Technology in Education.
         [paper]
  • Yi-Chia Wang, Mahesh Joshi and Carolyn Rosé. A Feature Based Approach to Leveraging Context for Classifying Newsgroup Style Discussion Segments. In Proceedings of ACL 2007, Poster Session.
         [paper]
  • Yi-Chia Wang, Carolyn Rosé, Mahesh Joshi, Frank Fischer, Armin Weinberger and Karsten Stegmann. Context Based Classification for Automatic Collaborative Learning Process Analysis. In Proceedings of 13th International Conference on Artificial Intelligence in Education (AIED 2007), Poster Session.
         [paper]
  • Rohit Kumar, Carolyn Rosé, Mahesh Joshi, Yi-Chia Wang, Yue Cui, Allen Robinson. Tutorial Dialogue as Adaptive Collaborative Learning Support. In Proceedings of the 13th International Conference on Artificial Intelligence in Education (AIED 2007).
         [paper]
  • 2006

  • Mahesh Joshi, Serguei Pakhomov, Ted Pedersen and Christopher Chute. A Comparative Study of Supervised Learning as Applied to Acronym Expansion in Clinical Reports. In Proceedings of the American Medical Informatics Association Annual Symposium (AMIA 2006).
         [paper]
  • Mahesh Joshi. Kernel Methods for Word Sense Disambiguation and Abbreviation Expansion in the Medical Domain. Masters' Thesis, University of Minnesota, Duluth. August 2006.
         [paper]
  • Mahesh Joshi, Serguei Pakhomov, Ted Pedersen, Richard Maclin and Christopher Chute. An End-to-end Supervised Target-Word Sense Disambiguation System. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06), Intelligent Systems Demonstration Session.
         [paper]
  • Mahesh Joshi, Ted Pedersen, Richard Maclin and Serguei Pakhomov. Kernel Methods for Word Sense Disambiguation and Acronym Expansion. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06), Student Abstract Papers.
         [paper]
  • 2005

  • Mahesh Joshi, Ted Pedersen and Richard Maclin. A Comparative Study of Support Vector Machines Applied to the Supervised Word Sense Disambiguation Problem in the Medical Domain. In Proceedings of the Second Indian International Conference on Artificial Intelligence (IICAI 2005).
         [paper]

    Contact Info

    maheshj@cs.cmu.edu



    This page last modified Wednesday, 12-Jun-2013 11:48:12 EDT


    Thanks to Leo Babauta of zen habits for the CSS template!