2007 North American Computational Linguistics Olympiad

Dragomir Radev

"As a teenager in Sofia, I spent a lot of my free time in the local "Filmotheque". I always wanted to become a movie director like Truffaut, Wenders, or Angelopoulos. That was until the day I learned about the Linguistics Olympiad. My high school was about to participate in it for the first time so there was still space on the team for those students who did well at the internal tryouts. Knowing a few foreign languages already, I had always been intrigued by their regularities and differences.

The contest seemed to fall at the right time. I ended up on the school team and won a couple of awards at the Bulgarian national contests. These were organized at the time by Prof. Ruslan Mitkov of the Bulgarian Academy of Sciences. I enjoyed the problems thoroughly - we had to decipher texts in obscure languages, figure out the Japanese calendar system, and "discover" vowel harmony in Hungarian and Turkish.

Twenty years later, here I am, doing research and teaching Computational Linguistics courses (http://tangra.si.umich.edu/clair) at the University of Michigan."

                                                                        Dragomir Radev

Information about Dragomir Radev

• Dr. Radev has a PhD in Computer Science from Columbia University.


• Dragomir R. Radev is an Associate Professor, School of Information, Department of Electrical Engineering and Computer Science, and Department of Linguistics at the University of Michigan, Ann Arbor.


• He joined U-M from IBM's TJ Watson Research Center in Hawthorne, NY. While at IBM, Dragomir was also an adjunct assistant professor in the Department of Computer Science at Columbia University in New York City.


• Research:
  - Research in CLAIR focuses on natural language processing, information retrieval, and network analysis.
  - Graph-based semi-supervised learning: Tumbl
  - Lexical networks and lexical centrality: LexRank, LexRankMead
  - Citation network analysis: BioNutch
  - Protein interaction extraction from text: ProtInter
  - Text summarization: MEAD, NewsInEssence, Resources, CSTBank, SUMMBANK
  - Analysis of the Blogosphere: Blog Analysis
  


• Latest Publications:
  - Rada Mihalcea and Dragomir R. Radev, editors. Textgraphs: Graph-based methods for NLP, New York City, 2006.
  - Jahna Otterbacher and Dragomir Radev. Fact-focused Novelty Detection: a Feasibility Study. In Poster session, 29th Annual ACM SIGIR Conference on Research and Development in Information Retrieval, Seattle, Washington, August 2006.
  - Jahna Otterbacher, Dragomir Radev, and Omer Kareem. News to Go: Hierarchical Text Summarization for Mobile Devices. In 29th Annual ACM SIGIR Conference on Research and Development in Information Retrieval, Seattle, Washington, August 2006.
  - Agam Patel and Dragomir R. Radev. Lexical similarity can distinguish between automatic and manual translations. In LREC, Genoa, Italy, May 2006.
  - Kevin M. Quinn, Burt L. Monroe, Michael Colaresi, Michael H. Crespin, and Dragomir R. Radev. An automated method of topic-coding legislative speech over time with application to the 105th-108th u.s. senate. In Midwest Political Science Association Meeting, 2006.