rada mihalcea    

home . research . publications . teaching . downloads . lit@unt . random . contact


research interests . projects . activities . invited talks . tutorials . workshops
[see also the publications and downloads pages for related information]


research group
My research group is the Language and Information Technologies group (LIT@UNT).

research interests
My research interests are in Natural Language Processing, Machine Learning, and Information Retrieval. I am currently working on:
  • Lexical Semantics (including: semantic similarity, word sense disambiguation, semantic parsing)
  • Graph-based Algorithms for Natural Language Processing (with applications to text summarization, word sense disambiguation, keyphrase extraction)
  • Building and Exploiting Parallel Texts, Multilingual NLP
  • Sentiment and Subjectivity Analysis, Computational Humour
  • Building Annotated Corpora with Volunteer Contributions over the Web


    My research projects are funded by the National Science Foundation, Google, the Texas Advanced Research Program, and ARDA-AQUAINT.


    current research projects
    SenseLearner tools for finding the meaning of all words in unrestricted text
    Teach-Computers data collection with volunteer contributions over the Web
    TextRank graph-based ranking algorithms for text processing
    Babylon methods for building and exploiting parallel texts
    Resources for word / sentence alignment
    Sentiment and Subjectivity Analysis monolingual and cross-lingual sentiment and subjectivity analysis
    Computational Humor computational approaches for humour recognition and generation
    SPOT Semantic Parsing for Open Text


    current activities
  • Journal of Natural Language Engineering (2007-2011)
  • Research on Language and Computation (2007-2011)
  • Journal of Interesting Negative Results in Natural Language Processing and Machine Learning editorial board (2006-present)
  • John Benjamins series on Natural Language Processing, advisory board
  • SIGNLL board member (2002-present)
  • Senseval/Semeval advising committee (2004-present)


    past activities
  • SIGLEX president (2004-2007)
  • Computational Linguistics editorial board (2005-2007)
  • Language Resources and Evaluation editorial board (2005-2006)
  • Guest editor for NLE Special Issue on Parallel Texts, 2005 (with Michel Simard)


    recent invited talks
  • Linking Documents to Encyclopedic Knowledge: Using Wikipedia as a Source of Linguistic Evidence, Dublin City University, February 8, 2008.
  • keynote at the International Conference on Linguistic Evidence, Tubingen, Germany, February 1, 2008.
  • Linking Documents to Encyclopedic Knowledge: Using Wikipedia as a Source of Linguistic Evidence, University of Toronto, January 30, 2008.
  • Learning Multilingual Subjective Language via Cross-Lingual Projections, Columbia University, New York, September 2007.
  • The Language of Humour, keynote at the Workshop on Cross-lingual Information Processing, Camogli, Italy, July 2007.
  • Using Wikipedia for Word Sense Disambiguation, keynote at the International Conference on Knowledge Engineering Principles and Techniques, Cluj-Napoca, Romania, June 2007.
  • Measures of Text Semantic Similarity, Sussex University, Brighton, United Kingdom, May 17, 2007.
  • A Picture is Worth Seven Thousand Words: Toward Communicating Simple Sentences using Pictorial Representations, Turing Center, Washington University, Seattle, Washington, April 17, 2007.
  • A Picture is Worth Seven Thousand Words: Toward Communicating Simple Sentences using Pictorial Representations, National Polytechnic Institute, Mexico City, March 20, 2007.
  • The Language of Humour, keynote at the NAACL workshop on Computational Approaches to Figurative Language, Rochester, NY, April 26, 2007.
  • Building Multilingual and Crosslingual Semantic Resources with Volunteer Contributions over the Web, invited presentation at the workshop on ``Multi-lingual semantic annotation: Theory and applications'', Saarland University, Saarbrucken, Germany, June 23, 2006.
  • Measures of Text Semantic Similarity, University of Oxford, Oxford, United Kingdom, June 16, 2006.
  • Measures of Text Semantic Similarity, University of Wolverhampton, Wolverhampton, UK, June 2006.
  • Random Walks on Text Structures, keynote at the International Conference on Intelligent Text Processing and Computational Linguistics, CICLing, Mexico City, Mexico, February 2006.
  • Text Processing with Graph-based Ranking Algorithms, Instituto Nacional de Astrofisica Optica y Electronica (INAOE), Puebla, Mexico, September 6, 2005.
  • Text Processing with Graph-based Ranking Algorithms, University of Ottawa, TAMALE Research Day, Ottawa, Canada, May 25, 2005.
  • Graph-based Algorithms for Text Processing, University of Memphis, Memphis, March 17, 2005.
  • Random Walks on Text Structures, University of Texas, Forum for Artificial Intelligence, Austin, February 24, 2005.
  • Using Your Algorithm to Solve My Problems, Google, Sunnyvale, December 16, 2004.
  • Making Sense Out of the Web, keynote at Lexical Resources and the Web for Word Sense Disambiguation, IBERAMIA, Puebla, Mexico, November 22, 2004.
  • Text Processing with Graph-based Ranking Algorithms, School of Libraries and Information Sciences, UNT, November 3, 2004.
  • Graph-Theory Meets Computational Linguistics: Text Processing with Graph-based Ranking Algorithms, keynote at EsTAL 2004, Alicante, Spain, October 21, 2004.
  • Text Summarization with Graph-based Ranking Algorithms, Microsoft Research, Seattle, September 10, 2004.
  • Text Summarization with Graph-based Ranking Algorithms, Xerox Research Center Europe, Grenoble, France, August 20, 2004.
  • Unsupervised Word Sense Disambiguation using Graph-based Ranking Algorithms, Istituto Trentino di Coltura ITC/IRST, Trento, Italy, August 4, 2004.
  • Graph-based Ranking Algorithms for Language Processing, USC/ISI, April 16, 2004 [abstract]
  • The Quest for Meaning, Berlin-Brandenburg Academy of Science, August 23, 2003.
  • The Web as Collective Mind: Building Large Annotated Corpora with Web Users' Help, invited presentation at the 1st Meaning Workshop, San Sebastian, Basque Country, April 11-12, 2003.
  • Using the Web for Word Sense Disambiguation, University of Minnesota, Duluth, October 24, 2002 [abstract]
  • Efficient Data Driven Methods for Word Sense Disambiguation, University of Ottawa, March 11, 2002 [abstract]


    tutorials
  • Words, meanings, and Emotions, tutorial at the Eurolan Summer School, Iasi, Romania, August 2007 (with Carlo Strapparava).
  • Graph-based Algorithms for Information Retrieval and Natural Language Processing, tutorial at RANLP 2005 Borovetz Bulgaria September 2005, HLT-NAACL 2006 New York City June 2006 (with Drago Radev).
  • How to add a new language on the NLP map, tutorial at EUROLAN 2005, Cluj-Napoca, Romania, August 2005 (with Vivi Nastase, Doina Tatar), IJCNLP 2008, Hyderabad, India, 2008.
  • Advances in Word Sense Disambiguation (with Ted Pedersen), tutorial at IBERAMIA 2004 Puebla Mexico November 2004, ACL 2005 Ann Arbor June 2005, AAAI 2005 Pittsburgh July 2005.


    workshops
  • NAACL 2007 workshop on Textgraphs: Graph-based Algorithms for Natural Language Processing, Rochester, April 2007. (with Chris Biemann, Irina Matveeva, Drago Radev)
  • NAACL 2006 workshop on Textgraphs: Graph-based Algorithms for Natural Language Processing, New York City, June 2006. (with Drago Radev)
  • ACL 2005 workshop on Building and Using Parallel Texts: Data Driven Machine Translation and Beyond, Ann Arbor, July 2005. (with Philipp Koehn, Joel Martin, Christof Monz, Ted Pedersen)
  • AAAI 2005 Spring Symposium on Knowledge Collection from Volunteer Contributors, March 2005. (with Timothy Chklovski, Pedro Domingos, Henry Lieberman, Push Singh)
  • Senseval-3, "3rd International Workshop on the Evaluation of Systems for the Semantic Analysis of Text", ACL, Barcelona, July 2004. (with Phil Edmonds)
  • HLT-NAACL 2003 Workshop on "Building and Using Parallel Texts: Data Driven Machine Translation and Beyond", Edomonton, May 2003. (with Ted Pedersen)
  • ACL 2002 Workshop on "Word Sense Disambiguation: Recent Advances and Future Directions", Philadelphia, July 2002. (with Phil Edmonds)


    recent program committees
  • Eurolan Doctoral Consortium 2007, EMNLP 2007, ACL 2007, AAAI 2007, NAACL 2007, Cicling 2007, Flairs 2007, ICWSM 2007.
  • EMNLP 2006 (area chair), LinkKDD 2006, ACL 2006, AAAI 2006, HLT/NAACL 2006, Cicling 2006, EACL 2006, AAAI 2006 Spring Symposium on Weblogs, Flairs 2006 track on Trends in NLP
  • HLT/EMNLP 2005, LinkKDD 2005, CoNLL 2005, AAAI 2005 (doctoral consortium), RANLP 2005, IJCAI 2005 (poster session, senior PC), ACL 2005, ACL 2005 (poster & demos) , AAAI-KCVC 2005, Cicling 2005, Flairs 2005
  • EMNLP 2004, NIPS 2004, Coling 2004, ACL 2004 (area chair) , IBERAMIA 2004 - WSD workshop CoNLL 2004, LREC 2004, Flairs 2004, Cicling 2004
  • DC-KCAP 2003, NIPS 2003, RANLP 2003, ACL 2003, CoNLL 2003, EACL 2003, EACL 2003 (research notes), FLAIRS 2003