Research Interests

  • Computational Linguistics.
  • Automatic analysis of child language.
  • Human Language Technology applications (e.g. dialogue systems, information extraction and speech recognition).
  • Multimodal processing and human communication dynamics.

For more details, see my research page and my list of publications.

Current and Recent Activities

  • I taught CSCI 544 Natural Language Processing, Spring 2014.
  • I taught CSCI 561 Foundations of Artificial Intelligence, Spring 2012, with Liang Huang.
  • I was Syntax and Parsing area co-chair for EACL 2012 (with Xavier Carreras).
  • I was a member of the discriminative language modeling team in the 2011 Johns Hopkins CLSP Summer Workshop.
  • I am an information officer for SIGPARSE, the ACL Special Interest Group on Natural Language Parsing.
  • I co-organize the ICT Machine Learning reading group with Louis-Philippe Morency.

Brief Bio

University of Southern California (2008-present)

I am a Research Assistant Professor at the USC Computer Science Department, and a Research Scientist and Project Leader at the USC Institute for Creative Technologies. I teach CSCI 544 Applied Natural Language Processing, and supervise a research group on computational models of natural language structure consisting of a few students and a senior research associate.

University of Tokyo (2006-2008)

Before joining USC I was a member of Tsujii Laboratory at the University of Tokyo. At Tsujii Lab, I worked on combining discriminative dependency parsing with HPSG, and on applying syntactic parsing in bioinformatics.

Carnegie Mellon University (PhD, 2006)

I got my PhD at Carnegie Mellon University in 2006. My thesis advisors were Alon Lavie (LTI) and Brian MacWhinney (Psychology). The other members of my thesis committee were Lori Levin (LTI), Jaime Carbonell (LTI), and John Carroll (University of Sussex, Department of Informatics).

My research at CMU involved the identification of grammatical relations, or GRs, (such as subjects, objects and adjuncts) in corpora of transcribed dialogues between children and parents. Most of these transcripts came from the CHILDES Database, but I also worked with transcripts from other sources.