swabha swayamdipta

swabha@cs.cmu.edu
185 Stevens Way, Box 352350, Seattle WA
me

I am a PhD student in the Language Technologies Institute at Carnegie Mellon University. My advisors are Noah Smith and Chris Dyer. My research interests are primarily in structured prediction for natural language, with a focus on semantic parsing. I find the problem of efficient search in an exponential space of complex structures very interesting. My current projects involve work on joint syntactic and semantic parsing.

In 2013, I graduated from a Masters program at Columbia University, where I was advised by Owen Rambow. During this period, I worked on detection of influence and power in online social media.

Since Aug 2015, I have relocated to Seattle, and am currently a visiting student at CSE in University of Washington, Seattle.

publications

  • Greedy, Joint Syntactic and Semantic Parsing with Stack LSTMs.
    Swabha Swayamdipta, Miguel Ballesteros, Chris Dyer and Noah A. Smith.
    SIGNLL Conference on Computational Natural Language Learning (CoNLL 2016). [Code] [Talk]

  • A Dependency Parser for Tweets.
    Lingpeng Kong, Nathan Schneider, Swabha Swayamdipta, Archna Bhatia, Chris Dyer and Noah A. Smith.
    Conference on Empirical Methods in Natural Language Processing (EMNLP 2014).

  • CMU: Arc-Factored, Discriminative Semantic Dependency Parsing.
    Sam Thomson, David Bamman, Jesse Dodge, Swabha Swayamdipta, Nathan Schneider, Chris Dyer and Noah A. Smith.
    International Workshop on Semantic Evaluation (SemEval 2014).

  • The CMU Machine Translation Systems.
    Austin Matthews, Chris Dyer, Alon Lavie, Greg Hanneman, Waleed Ammar, Archna Bhatia, Swabha Swayamdipta, Eva Schlinger and Yulia Tsvetkov.
    Workshop on Machine Translation (WMT 2014).

  • The Pursuit of Power and its Manifestation in Written Dialog.
    Swabha Swayamdipta and Owen Rambow.
    IEEE International Conference of Semantic Computing (ICSC 2012).

  • teaching

  • I TAed for Undergrad NLP (11-411) taught by Chris Dyer, Alon Lavie and Shomir Wilson, in the Spring of 2015.
  • With Sam Thomson, I gave a lecture on the Chu-Liu-Edmonds algorithm for Algorithms for NLP in the Fall of 2014.
  • others

    I am a strong supporter of using Beamer for slides; even though there is a steep learning curve, it is immensely rewarding to see the end product.