Current Students

• Jack Quigley (May 2025), Gaelic (Irish) NLP, topic to be determined
• Shujauddin Rafai Syed (May 2026), SemEval-2025 Task 7, topic to be determined

Alumni

• Sam Akrah, M.S. October 2023.

• Anna Martin, M.S. May 2022, now a PhD student at the University of Minnesota, Twin Cities.

• Zakaria Daud, M.S. May 2021.

• Saptarshi Sengupta M.S. Summer 2020. Saptarshi will be joining a PhD program in Fall 2020.

• Madiha Mirza M.S. January 2020.

• Shuning Jin B.S. May 2019.

• Xinru Yan M.S. April 2019. Xinru joined the MS in Languages Technologies Program at CMU in Fall 2018.

• Swathi Vallabhajosyula M.S. July 2018 . Swathi will join the PhD program in Computer Science at The Ohio State University as of Fall 2019.

• Zhenduo Wang M.S. July 2018 in Math/Stat, co-advised with Yang Li. Zhenduo has been a PhD student in Computer Science at the University of Utah since Fall 2018.

• Jon Rusert M.S. May 2017. Jon is a PhD student at the University of Iowa as of Fall 2017. Read Jon's Master's Thesis on Language evolves, so should WordNet - Extending WordNet with Senses from Out of Vocabulary Lemmas.

• Mugdha Choudhari M.S. August 2012. Now at Yummly. Read Mugdha's Master's Thesis on Extending the Hirst and St-Onge Measure of Semantic Relatedness for the Unified Medical Language System.

• Ying Liu Post-Doctoral Researcher (2009-2012), co-supervised with Serguei Pakhomov. Now at City of Hope in Los Angeles.

• Yanbo Xu (M.S. July 2011 in Math/Stat, co-advised with Kang James ) Yanbo is now a PhD student at Carnegie-Mellon University in the Language Technologies Institute as of Fall 2010. Read Yanbo's project report on Random Walk on WordNet to Measure Lexical Semantic Relatedness.

• Varada Kolhatkar M.S. August 2009. Varada completed her PhD in March 2015 at the University of Toronto in the Department of Computer Science. Her advisor was Graeme Hirst. Read Varada's Master's thesis on An Extended Analysis of a Method of All Words Sense Disambiguation.

• Mahesh Joshi M.S. August 2006 [co-advised with Rich Maclin]. Mahesh will be joining eBay as an Applied Research in Summer 2013. Mahesh defended his PhD dissertation in May 2013 at Carnegie Mellon University in the Language Technologies Institute. His advisers were William Cohen and Carolyn Rose. Read Mahesh's thesis on Kernel Methods for Word Sense Disambiguation and Abbreviation Expansion in the Medical Domain.

• Apurva Padhye M.S. August 2006. Now at Brightcove in Cambridge, MA. Until September 2009 was a software engineer at Endeca in the Boston area. Read Apurva's thesis on "Comparing Supervised and Unsupervised Classification of Messages in the Enron Email Corpus". As a part of her thesis work, Apurva manually classified more than 3,000 email messages by topic.

• Anagha Kulkarni M.S. July 2006 and former Graduate Research Assistant. Since Fall 2013 Anagha has been an Assistant Professor in the Department of Computer Science at San Francisco State University. Anagha defended her PhD dissertation in October 2013 at Carnegie Mellon University in the Language Technologies Institute. Her advisor was Jamie Callan. Read Anagha's Master's thesis on Unsupervised Context Discrimination and Automatic Cluster Stopping. See the slides from Anagha's defense. All of the ideas in her thesis have been implemented in the SenseClusters package. You can even experiment with her thesis data. Anagha was an intern at the Mayo Clinic in the Summer of 2005. See her final presentation and report.

• Saiyam Kohli M.S. July 2006. Now working in Los Angeles at SDL/Language Weaver. Read Saiyam's report on Introducing an Object Oriented Design to the Ngram Statistics Package. All of Saiyam's work can be found in the Ngram Statistics Package. Saiyam also worked on a project with me in the Summer of 2005 developing WordNet::Similarity::Visual.

• Pratheepan Raveendranathan M.S. July 2005. Now a Lead Business Systems Analyst with the Business Intelligence Group, Global Business Solutions at Ecolab in St. Paul, Minnesota. Read Prath's thesis on Identifying Sets of Related Words from the World Wide Web, and see the slides from Prath's thesis defense. This work is implemented in the GoogleHack package.

• Jason Michelizzi M.S. July 2005 and former Graduate Research Assistant. Now a Naval Aviator in the US Navy. Read Jason's thesis about "Semantic Relatedness Applied to All Words Sense Disambiguation". Jason's method of all words disambiguation is implemented in the Perl module WordNet::SenseRelate::AllWords Jason was also responsible for significant improvements to WordNet::Similarity.

• Justin Chase, B.S. May 2005 and former UROP student. You can see Justin's UROP project about Advanced Searching for Online Resources here.

• Bridget McInnes M.S. December 2004. Bridget defended her Ph.D. dissertation in September of 2009 at the University of Minnesota, where Ted Pedersen and John Carlis were her advisors. Thereafter she was a post-doc at the University of Minnesota, working with Ted Pedersen and Serguei Pakhomov until November 2011. Bridget will become an Assistant Professor in the Department of Computer Science at Virginia Commonwealth University in Fall 2014. She was previously employed at Securboration as a Computational Linguist. Read Bridget's M.S. thesis about Extending the Log-Likelihood Ratio to Improve Collocation Identification. You can find Bridget's code to carry this out with NSP here. Bridget was an intern at the Mayo Clinic in the Summers of 2003 and 2004. You can a presentation she made regarding her 2003 internship here.

• Amruta Purandare M.S. August 2004 and former Graduate Research Assistant. Now on the Research Staff at Singapore Management University (SMU). Earned a M.S. in August 2006 in Intelligent Systems at the University of Pittsburg. Read Amruta's thesis about Word Sense Discrimination by Clustering Similar Contexts here. All of Amruta's thesis work was done using her SenseClusters package. See the slides from Amruta's thesis defense.

• Saif Mohammad M.S. August 2003. Saif defended his Ph.D. dissertation in January 2008 at the University of Toronto, where Graeme Hirst was his advisor. Saif was then a post-doc at the University of Maryland (working with Bonnie Dorr until September 2009). He is now a Research Officer at the National Research Council of Canada. Read Saifs's M.S. thesis about Combining Lexical and Syntactic Features for Supervised Word Sense Disambiguation and find many of the tools used in this work here. You can find all of the sense-tagged text used in this thesis here. See the slides from Saif's thesis defense.

• Siddharth "Sid" Patwardham M.S. August 2003. Sid defended his Ph.D. dissertation in September 2009 at the University of Utah, where Ellen Riloff was his advisor. He is now a Senior Software Engineer at IBM TJ Watson Lab working on the Deep QA project. Read Sid's thesis about Incorporating Dictionary and Corpus Information into a Context Vector Measure of Semantic Relatedness here and find the implementation of these ideas here. See the slides from Sid's thesis defense. Sid was an intern at the Mayo Clinic in the Summer of 2003. Read his final report on that experience.

• Brian Rassier, B.S. May 2003 and former Undergraduate Research Assistant and UROP student. Now working at Ing Bank in St. Cloud. See Brian's various projects here.

• Satanjeev "Bano" Banerjee M.S. December 2002 and former Graduate Research Assistant. Bano defended his PhD at Carnegie Mellon University in the Language Technologies Institute in 2011 and is now employed at Twitter Research. Read Bano's thesis about Adapting the Lesk Algorithm for Word Sense Disambiguation to WordNet. Find the implementation of these ideas here.

• Nitin Varma, M.S. December 2002. Nitin is now in Baltimore, working for the software QA group at CitiFinancial. Read Nitin's thesis about extending the Kvec Algorithm for Finding Translations in Parallel Text. One of the results of the thesis is the K-vec++ package, available here! .

• Aditi Paluskar, M.S. November 2001. Now a Software Engineer for Wetfeet in the Bay Area. After graduating from UMD, Aditi went to the University of Missouri-Rolla and earned a Master's in Engineering Management. Read about Aditi's MS project User-Level Control Of Scheduling in a Micro Kernel Operating System ". This involved the use of Solaris Minix, which is still one of my favorite environments for Operating System projects and experiments.

A Few Pictures