MEGRASP

(A syntactic parser for CHILDES trascripts)

 

Kenji Sagae

Dept. of Computer Science, University of Tokyo

 

MEGRASP is a dependency parser for identification of grammatical relations in child language transcripts in the CHILDES Database.

 

MEGRASP will soon be distributed within CLAN, a collection of utilities for editing and  processing child language transcripts (including the MOR morphological analyzer and the POST part-of-speech tagger).  This page contains only MEGRASP itself, which requires input files in CHAT format (PDF link), with part-of-speech tags produced by POST (or manually assigned).  If this does not sound familiar, consult the main CHILDES web site.

 

Download

MEGRASP v0.7 (released June 15, 2007)

· MS-Windows

· Cygwin

· Linux

· Mac OSX

· Source code

 

After downloading and unzipping the archive for your platform, please look at the README file (README.txt in the Windows distribution) for instructions on running the parser.

 

Please feel free to contact me at sagae+megrasp@cs.cmu.edu with questions, comments, requests and bug reports.

 

For more information about MEGRASP, see the following paper (please cite it in work based on MEGRASP output).

 

Sagae, K., Davis, E., Lavie, A., MacWhinney, B. and Wintner, S. 2007. High-accuracy annotation and parsing of CHILDES transcripts. Proceedings of the ACL-2007 Workshop on Cognitive Aspects of Computational Language Acquisition. Prague, Czech Republic.

 

A (slightly out-of-date) description of the grammatical relations used by MEGRASP is available here.