Contextual Self-organizing Map package.

[Xiaowei]

Dear Colleagues,

We (Xiaowei Zhao, Ping Li and Teuvo Kohonen) have just developed a
software package (CTM_pack) that can automatically derive semantic
representations of words from text copora. The algorithm relies on the
analyses of contextual information extracted from a text corpus,
specifically, analyses of word co-occurrences in large-scale
electronic database of text. Here a target word is represented as the
combination of the average of all the words preceding the target and
all the words following it in a text corpus. The semantic
representation of the target words can be further presented to a self-
organizing map (SOM, Kohonen, 2001), an unsupervised neural network
model that provides efficient data extraction and representation. We
present demos of how the method is applied to extract semantic
representations for both Chinese and English words. Such a
representation system can be used for a variety of purposes, including
computational modeling of language acquisition and processing. It is
also our hope that scientists working in the field of child language
development can find this system useful in their studies.

This work has been previously presented at the 2009 Society for
Computers in Psychology. And a full paper described this system is
under review now.

If you are interested in this tool, please go to:
http://sites.google.com/site/xiaoweizhao/tools to download it. The
program is written in MatLab, and should be run under the MatLab
Enviroment. Your comments and suggestions on the  program are
extremely welcome!


Best wishes,
Xiaowei Zhao


Xiaowei Zhao, Ph.D.
Visiting Assistant Professor

Department of Psychology
Colgate University
Hamilton, NY 13346

Phone: 315-228-6717
Email: xzhao at colgate.edu

-- 
You received this message because you are subscribed to the Google Groups "Info-CHILDES" group.
To post to this group, send email to info-childes at googlegroups.com.
To unsubscribe from this group, send email to info-childes+unsubscribe at googlegroups.com.
For more options, visit this group at http://groups.google.com/group/info-childes?hl=en.