Dan Bikel’s Home Page

Aside from the software subpage, this page is somewhat out of date. Please visit www.danbikel.com for a more up-to-date page.

email: dan AT bikel DOT net

Table of Contents of this page:

Academics
Research
Software
My Album of Original Music
My Former Job

Academics

Return to Table of Contents.

Schools From Which I’ve Graduated From Them

University of Pennsylvania

Department of Computer and Information Science (M.S. 2000, Ph.D. 2004)

Harvard University

Department of the Classics (A.B. 1993)
Division of Engineering and Applied Sciences (Graduate Student in the Special Student Program, 1993-1996)

Phillips Exeter Academy (highest honors, Classics diploma 1989)

Research

Return to Table of Contents.

My general area of research is the investigation of statistical methods for natural language processing. I am particularly interested in the analysis of generative parsing models, and investigating the use of (largely) language-independent parsing models with multiple languages. My parsing engine is currently capable of emulating the state-of-the-art models of Mike Collins in English, and can also deliver state-of-the-art parses in Chinese, Arabic and, somewhat obscurely, Classical Portugese. Work is underway to extend it for use with the Korean Treebank.

My advisor is Mitch Marcus.

Here is my curriculum vitae (PDF).

On May 10th, 2010, I joined Google’s New York City office as a Research Scientist. Google is an exciting startup company working on a variety of interesting problems, some related to search. Perhaps you’ve heard of it already…

Ph.D. Dissertation

On August 9th, 2004, I successfully defended my thesis.

On the Parameter Space of Generative Lexicalized Statistical Parsing Models. University of Pennsylvania. 2004. (PS) (PDF)
Click here to download my defense presentation (sorry: it is in PowerPoint format ... all the non-proprietary exported formats messed up too many elements of the presentation).

Publications

Journal Articles

Daniel M. Bikel. 2004. Intricacies of Collins’ Parsing Model. (PS) (PDF)
in Computational Linguistics, 30(4), pp. 479-511.
Daniel M. Bikel, Richard Schwartz and Ralph M. Weischedel. 1999. An Algorithm that Learns What’s in a Name (PS) (PDF)
in the Machine Learning Journal Special Issue on Natural Language Learning

Conference Articles

Daniel M. Bikel. 2004. A Distributional Analysis of a Lexicalized Statistical Parsing Model. (PS) (PDF)
in the proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP 2004)
(see ch. 7 of my Ph.D. thesis for an expanded version of this paper)
David Chiang and Daniel M. Bikel. 2002. Recovering Latent Information in Treebanks (PS) (PDF)
in the proceedings of COLING 2002
Daniel M. Bikel. 2002. Design of a Multi-lingual, Parallel-processing Statistical Parsing Engine (PS)
in the proceedings of HLT 2002
Daniel M. Bikel. 2000. A Statistical Model for Parsing and Word-Sense Disambiguation (PS) (PDF)
in the proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora
Daniel M. Bikel, Scott Miller, Richard Schwartz and Ralph Weischedel. 1997. Nymble: a High-Performance Learning Name-finder (PS) (PDF) (Abstract)
in the proceedings of the Conference on Applied Natural Language Processing, ’97

Workshop Articles

Daniel M. Bikel and David Chiang. 2000. Two Statistical Parsing Models Applied to the Chinese Treebank (PS) (PDF)
in the proceedings of the Second Chinese Language Processing Workshop
Daniel M. Bikel. 2000. A Statistical Model for Parsing and Word-Sense Disambiguation (PS) (PDF)
in the proceedings of the Student Research Workshop at ACL 2000