Tejaswini Deoskar

Department of Linguistics
Cornell University
203 Morrill Hall
Ithaca, New York 14850 USA
email: t d 7 2   AT   c o r n e l l   DOT   e d u

Research Interests

Computational Linguistics, syntax of SOV languages, South Asian languages (Hindi, Marathi)

  • Stochastic modelling of natural language, including probabilistic parsing, induction of PCFGs from large unannotated data, large-scale lexical acquisition
  • Semi-supervised estimation methods.
  • Richer grammars for robust probabilistic parsing.
  • Syntax of SOV languages, Complex Predicates in South Asian Languages
    •  I work on probabilistic models of natural language grammars. I am interested in building richer probabilistic models for parsing and in the estimationg of accurate PCFGs from unannotated data. Currently I am experimenting with using a modified version of the inside-outside algorithm along with a treebank-trained PCFG to learn lexical information from large sources of data. I am also interested in the syntax and typology of languages with Subject-Verb-Object word order, in particular languages spoken in the subcontinent of South-Asia.

    CV

    Dissertation : Corpus Induction of Lexicons using Inside-Outside and Lexical Transformations
    Advisor: Mats Rooth web
    Minor: Cognitive Science Cognitive Science at Cornell

    Current Projects

  • Building an enhanced Penn Treebank-based unlexicalized PCFG
  • Learning valences of low frequency verbs using Inside-Outside
  • EM based clustering of the Local Syntactic contexts of words

    • Papers

    Deoskar Tejaswini and Rooth, Mats. 2008. Induction of Treebank-Aligned Lexical Resources. Proceedings of Sixth International Conference on Language Resources and Evaluation. Marrakech. Morocco.

    Deoskar, Tejaswini and Rooth, Mats. 2007. Corpus Induction of Lexicons for Treebank PCFGs by Inside-Outside Estimation and Frequency Transformations. Ms. [pdf]

    Deoskar, Tejaswini. 2006. Marathi Light Verbs. Proceedings of the 36th Annual Meeting of the Chicago Linguistics Society. [pdf]

    A preliminary study on the phonological adaptation of speakers of Indian English when exposed to American English. [pdf]

    A paper on Serial Verbs in Khoekhoe [pdf]

    Teaching

    Spring 2008 and 2006: TA, Introduction to Semantics and Pragmatics
    Fall and Spring 2005: Instructor, Biological Foundations of Language (Freshman Writing Seminar)
    Spring 2004: TA, Introduction to Hindi, Intermediate Hindi
    Fall 2005: TA, Introduction to Hindi

    Work Experience

    2001 to 2002: Developed applications in Java to create meta-directories for telecom databases and devices using the LDAP (Lightweight Directory Access Protocol). Also worked as a consultant to design and deploy metadirectory products (Meta-Connect).
    1997 to 2001: Worked as an embedded systems designer to build a CCD Camera controller for the IUCAA telescope at Giravali (Maharashtra, India). Also worked on interfacing the CCD camera and controller to a Linux network for control and image acquisition.
    1996 to 1997: Worked as a consultant to troubleshoot problems with computer hardware. Network administration of unix and windows networks.


    Links

    Cornell NLP Page
    IUCAA Observatory, Giravali, India
    hazaaron khwahishe aisi ke har khwahish pe dam nikle
    bahut nikle mere armaan, lekin phir bhi kam nikle