Experienced-Based Language Acquisition

CONTACT:
Brian E. Pangburn, Ph.D.
The Pangburn Company, Inc.
P.O. Box 900
New Roads, LA 70760-0900
Phone: 225.638.4752
Fax: 225.638.4773
E-Mail: ebla@greatmindsworking.com
Web Site: http://www.greatmindsworking.com


SUMMARY:
Experience-Based Language Acquisition (EBLA) is an open source software
system that enables a computer to learn simple language from scratch based
on visual perception. It is the first "grounded" language system capable of
learning both nouns and verbs. Moreover, once EBLA has established a
vocabulary, it can perform basic scene analysis to generate descriptions of
novel videos.


DETAILS:
New Roads, LA -- February 14, 2003 -- Announcing Experience-Based Language
Acquisition (EBLA), an open source software system designed to investigate
how computers might be enabled to understand natural language in a more
humanlike way. Based, in part, on cognitive development in infants, EBLA is
a computational framework for visual perception and grounded language
acquisition. EBLA can "watch" a series of short videos and acquire a simple
language of nouns and verbs corresponding to the objects and object-object
relations in those videos. Upon acquiring this protolanguage, EBLA can
perform basic scene analysis to generate descriptions of novel videos.

The general architecture of EBLA is comprised of three stages: vision
processing, entity extraction, and lexical resolution. In the vision
processing stage, EBLA processes the individual frames in short videos,
using a variation of the mean shift analysis image segmentation algorithm to
identify and store information about significant objects. In the entity
extraction stage, EBLA abstracts information about the significant objects
in each video and the relationships among those objects into internal
representations called entities. Finally, in the lexical acquisition stage,
EBLA extracts the individual lexemes (words) from simple descriptions of
each video and attempts to generate entity-lexeme mappings using an
inference technique called cross-situational learning. EBLA is not primed
with a base lexicon, so it faces the task of bootstrapping its lexicon from
scratch.

While there have been several systems capable of learning object or event
labels for videos, EBLA is the first known system to acquire both nouns and
verbs using a grounded computer vision system.

EBLA was developed in conjunction with the Robotics Research Laboratory at
LSU (http://bit.csc.lsu.edu/~rrl/). It is written entirely in Java and uses
a PostgreSQL database as a backend. The complete source code is available
from the SourceForge EBLA project site
(http://www.sourceforge.net/projects/ebla/).

For more information on EBLA, please visit GreatMindsWorking.com
(http://www.greatmindsworking.com), a web site dedicated to research on
computer models of human language acquisition.