USC Information Sciences Institute
4676 Admiralty Way,
Suite 1001
Marina del Rey, CA - 90292-6601 Phone: (310) 448-9391 E-mail: rahul [at] isi [dot] edu
About me:
I am a PhD candidate at the University
of Southern California (USC) and a Graduate Research Assistant
in the Natural
Language Group at the Information Sciences
Institute (ISI). My adviser
is Dr. Eduard Hovy.
I started my PhD at USC in August 2006. I defend my
PhD thesis, titled "Learning Paraphrases from Text", in April 2009.
Before entering the PhD program at USC, I was a Sr. Programmer
Analyst at USC/ISI from June 2004 to July 2006. I completed my
Master's degree in
Computer Science at USC in May
2004. Before that, I studied at the Visvesvaraya Regional College of Engineering (VRCE), now known as the
Visvesvaraya National Institute of Technology
(VNIT), where I earned my Bachelor's degree in Computer Science in July
2002.
Research Interests:
I am interested in the general areas of natural language processing and machine
learning. Specifically, I am interested in large-scale text
mining, unsupervised/weakly-supervised knowledge acquisition, and
information extraction.
I like working with very large amounts of data: I have worked
with corpora of sizes ranging from 150GB (25 billion words) to
over a 1TB (over 100 billion words).
I am currently working on automatically learning and
filtering paraphrases from large monolingual corpora.
In the past, I have worked on statistical shallow
semantic parsing and generation for virtual human
environments, spelling variants generation, and information
retrieval. I also helped in running a large multi-university
annotation effort - Ontonotes - at USC/ISI.
Partha Pratim Talukdar, Joseph Reisinger, Marius Pasca, Deepak
Ravichandran, Rahul Bhagat, Fernando Pereira.
"Weakly Supervised Acquisition of Labeled Class Instances using Graph Random Walks"
In Proceedings of the EMNLP Honolulu, Hawaii. 2008. [pdf]
Rahul Bhagat and Deepak Ravichandran
"Large Scale Acquisition of Paraphrases for Learning Surface Patterns"
In Proceedings of Association for Computational
Linguistics (ACL). Columbus, OH. 2008. [pdf]
2007
Rahul Bhagat, Patrick Pantel, Eduard Hovy
"LEDIR: An Unsupervised Algorithm for Learning Directionality
of Inference Rules"
In Proceedings of Conference on Empirical Methods in
Natural Language Processing (EMNLP). Prague, Czech
Republic. 2007. [pdf]
Rahul Bhagat and Eduard Hovy
"Phonetic Models for Generating Spelling Variants"
In Proceedings International Joint Conference of Artificial Intelligence
(IJCAI). Hyderabad, India. 2007. [pdf]
Patrick Pantel, Rahul Bhagat, Bonaventura Coppola, Timothy Chklovski, Eduard Hovy
"ISP: Learning Inferential Selectional Preferences"
In Proceedings of North American Association for Computational Linguistics / Human Language Technology (NAACL/HLT). Rochester, NY. 2007.
[pdf]
2005
Rahul Bhagat, Anton Leuski and Eduard Hovy
"Shallow Semantic Parsing despite Little Training Data"
In the ACL/SIGPARSE 9th International Workshop on Parsing Technologies, Vancouver,
B.C., Canada. 2005. [pdf]
David Traum, William Swartout, Jonathan Gratch, Stacy Marsella, Patrick Kenney, Eduard Hovy, Shri Narayanan, Ed Fast, Bilyana Martinovski,
Rahul Bhagat, Susan Robinson, Andrew
Marshall, Dagen Wang, Sudeep Gandhe and Anton Leuski.
"Demo Submission: Virtual Humans for non-team interaction training"
In the ACL/ISCA 6th SIGdial Workshop on Discourse and Dialogue. 2005. [pdf]
Rahul Bhagat, Anton Leuski and Eduard Hovy
"Shallow Semantic Parsing despite Little Training Data"
Technical Report. 2005. [pdf]
2003
Anton Leuski, Douglas W. Oard, and Rahul Bhagat.
"eArchivarius: Accessing collections of electronic mail"
In Proceedings of ACM SIGIR, pages 468-469, Toronto, Canada, 2003. [pdf]