Lijun Feng


I joined the Department of Biomedical Informatics at Columbia University since November 2010, working as a post-doctoral research scientist with
Noemie Elhadad on emotion detection and classification in transcripts from patient support group meetings. 

My research interests lie in natural language processing (NLP) and machine learning applications. I've done extensive work on text categorization, sentiment analysis and classification, automatic readability assessment, text comprehension and text simplification.

I completed my Ph.D. at the Graduate Center of the City University of New York (CUNY) in Fall 2010, where I worked with Matt Huenerfauth on automatic readability assessment. My thesis research combines NLP and machine learning techniques to build and evaluate an automatic text readability assessment tool, both for general audience, and adult readers with intellectual disabilities in particular. In addition to well studied lexical and syntactic features, my research pays special attention to local and global semantic text properties at various  discourse levels that capture and reflect important comprehension processes crucial for successful text understanding. For high level details, see abstract of my thesis.

 Before entering CUNY, I obtained an M.A. in Computer Science from Brooklyn College in May 2005. 

Publications

  • Martin Jansche, Lijun Feng and Matt Huenerfauth (forthcoming, October 2010).
    Reading Difficulty in Adults with Intellectual Disabilities: Analysis with a Hierarchical Latent Trait Model.
    In Proceedings of the 12th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2010), Orlando, Florida, USA.
    [view] [download PDF]

  • Lijun Feng, Martin Jansche, Matt Huenerfauth and Noémie Elhadad (2010).
    A Comparison of Features for Automatic Readability Assessment.
    In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), Beijing, China.
    [view] [download PDF from ACL]
      
  • Matt Huenerfauth, Lijun Feng, and Noémie Elhadad (2009).
    Comparing Evaluation Techniques for Text Readability Software for Adults with Intellectual Disabilities.
    In Proceedings of the 11th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2009), Pittsburgh, Pennsylvania, USA.
    [view] [download PDF] [ACM digital library]
  • Lijun Feng, Noémie Elhadad, and Matt Huenerfauth (2009).
    Cognitively Motivated Features for Readability Assessment.
    In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2009), Athens, Greece.
    [view] [download PDF from ACL]

  • Lijun Feng (2008).
    Automatic Readability Assessment for People with Intellectual Disabilities.
    In 10th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2008), Doctoral Consortium. Halifax, Nova Scotia, Canada.
    [view] [download PDF]
    Also appeared in ACM SIGACCESS Accessibility and Computing 93: 84-91, Januay 2009.  [ACM digital library]

Thesis Work

Contact

Send me an email

Sign in  |  Terms  |  Report Abuse  |  Print page  |  Powered by Google Sites