My broad research interests are in the area of computational linguistics and natural language processing. In particular, I am interested discourse understanding, anaphora resolution, abstract anaphora resolution, and word-sense disambiguation.
My Ph.D. dissertation focuses on developing computational methods for resolving shell nouns. Shell nouns are abstract nouns, such as fact, issue, idea, and problem, which facilitate efficiency in text by avoiding repetition of long stretches of text. An example is shown in (1).
-
(1)New York is one of only three states that do not allow some form of audio-visual coverage of court proceedings. Some lawmakers worry that cameras might compromise the rights of the litigants. But a 10-year experiment with courtroom cameras showed that televised access enhanced public understanding of the judicial system without harming the legal process. New York’s backwardness on this issue hurts public confidence in the judiciary...
Here, the shell noun phrase this issue can only be interpreted with the help of the bold text in the first sentence. If we want to build a computational system to understand a discourse like this it is important to automatically identify links between shell noun phrases and their shell content. My dissertation addresses this research problem.
Here are the related publication.
Varada Kolhatkar and Graeme Hirst. Resolving shell nouns. To appear in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, page to appear, Doha, Qatar, October 2014. [ pdf ] [ slides ] [ video ]
Varada Kolhatkar, Heike Zinsmeister, and Graeme Hirst. Interpreting anaphoric shell nouns using antecedents of cataphoric shell nouns as training data. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 300–310, Seattle, Washington, USA, October 2013.
Varada Kolhatkar, Heike Zinsmiester and Graeme Hirst. Annotating anaphoric shell nouns with their antecedents. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 112--121, Sofia, Bulgaria, August 2013. Association for Computational Linguistics.
Varada Kolhatkar and Graeme Hirst. Resolving “this-issue” anaphora. In Proceedings of the 2012 Conference on Empirical Methods in Natural Language Processing, pages 1255--1265, Jeju Island, Korea, July 2012. Association for Computational Linguistics.
[ pdf ] [ slides ] [data available on request]
I have also worked on Word Sense Disambiguation. Try our all-words WSD system here. The related publications are:
Varada Kolhatkar. An Extended Analysis of a Method of All Words Sense Disambiguation. Master’s thesis, University of Minnesota, Duluth, August 2009.
[ pdf ] [ slides ]
Ted Pedersen and Varada Kolhatkar. WordNet::SenseRelate::AllWords - a broad coverage word sense tagger that maximizes semantic relatedness. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Demonstration Session, pages 17–20, Boulder, Colorado, June 2009. Association for Computational Linguistics. [ pdf ] [system]
In summer 2008 (June-August 2008), I participated in JHU Summer School and Workshop held by the Center of Language and Speech Processing at Johns Hopkins University. Here is the related publication.
W. Spiegl, G. Stemmer, E. Lasarcyk, V. Kolhatkar, A. Cassidy, B. Potard, S. Shum, Y. Chol Song, P. Xu, P. Beyerlein, J. Harnsberger, E. Nöth. Analyzing Features for Automatic Age Estimation on Cross-Sectional Data. Interspeech, Brighton 2009.
[ pdf ]
