Home | Lalindra De Silva

I'm a PhD student in the School of Computing, University of Utah. My primary research interests are in Natural Language Processing and Machine Learning. Specifically, I'm interested in analyzing (mainly) microblogs (e.g., Twitter) and other public domain data sources to study the progression of major public events (e.g., civil unrest activities). With my advisor, Prof. Ellen Riloff, I currently research on the topic of event discovery and learning event precursors to predict how/when these major events come into fruition. In the early days of my graduate life, I've worked on information extraction with a focus on bio-medical domain and question answering systems for reading comprehension. I'm also a member of the NLP group in the University of Utah.

Prior to joining the University of Utah, I completed my undergraduate degree in computer science from the School of Computing of the University of Colombo, Sri Lanka in 2009. During my undergraduate days, I conducted research on building frameworks for assisting easy development of web ontologies using free resources such as the Wikipedia.

I currently live in Salt Lake City with my wife, who is also a PhD student in the Scientific Computing Institute of the University of Utah.

Here's my resume in pdf format [Updated: 08/2013]

Research

Here's a list of my publications in reverse chronological order.

Ellen Riloff, Ashequl Qadir, Prafulla Surve, Lalindra De Silva, Nathan Gilbert and Ruihong Huang, Sarcasm as Contrast between a Positive Sentiment and Negative Situation, To appear in proceedings of the International Conference on Empirical Methods in Natural Language Processing (EMNLP) 2013, Seattle, Washington, USA [pdf, bib]
Ryan Compton, Craig Lee, Tsai-Ching Lu, Lalindra De Silva and Michael Macy, Detecting Future Civil Unrest Events from Unprocessed Twitter Data, In proceedings of the IEEE Intelligence and Security Informatics (ISI) 2013, Seattle, Washington, USA [pdf, bib]
Lalindra De Silva, Thomas Ginter, Tyler Forbush, Neil Nokes, Brian Fay, Ted Mikuls, Grant Cannon and Scott DuVall, Extraction and Quantification of Pack-years and Classification of Smoker Information in Semi-structured Medical Records, In proceedings of the International Conference in Machine Learning (ICML) 2011: Workshop on Learning from Unstructured Clinical Text, Washington, USA [pdf, bib]
Lalindra De Silva and Lakshman Jayaratne, WikiOnto: A System For Semi-automatic Extraction And Modeling Of Ontologies Using Wikipedia XML Corpus, In proceedings of the International Conference on Semantic Computing (ICSC) 2009: Workshop on Semantic Web Information Management, Berkeley, California, USA [pdf, bib]
Lalindra De Silva and Hiran Ekanayake, Behavior-based Robotics and the Reactive Paradigm - A Survey, In proceedings of the International Conference on Computer and Information Technology (ICCIT) 2008: Workshop on Data Mining and Artificial Intelligence, Khulna, Bangladesh [pdf, bib]
Lalindra De Silva and Hiran Ekanayake, Behavior Architectures for Reactive Robots, In proceedings of the International Information and Technology Conference (IITC) 2008, Colombo, Sri Lanka (Poster Presentation)

Courses

I've taken the following courses during my graduate studies.

Machine Learning	Advanced Scientific Computing I
Natural Language Processing	Advanced Scientific Computing II
Artificial Intelligence	Network Security
System Identification for Robotics	Computer Architecture
Advanced Seminar: Robotics	Topics in Machine Learning
Formal Methods in System Design	Geometric Computation for Motion Planning

Personal

I come from Sri Lanka, a beautiful island located just south of the Indian subcontinent and just above the equator. It's a land of unrivaled natural beauty, fascinating people and it flaunts rich cultural and historic footprints of over 2500 years.

Lalindra De Silva

alnds [AT] cs [DOT] utah [DOT] edu

Research

Courses

Personal