CDP: A Connectionist Deterministic Parser A Dissertation Proposal

Authors

Kanaan A. Faisal, Washington University in St. Louis

Document Type

Technical Report

Publication Date

1989-08-01

Filename

WUCS-89-33.pdf

Technical Report Number

WUCS-89-33

Abstract

We propose to address problems related to the problem of Natural Language Processing. Neural networks approach will be used in attaching these problems. In this proposal a number of problems are considered: parsing of ill-formed sentences in addition to well-formed sentences, resolutions of some lexical ambiguities using syntactic context, and parsing of sentences sequentially over an input stream which is unbounded in length. Two network training approaches will be examined. Deductive training, based on grammar rules, and inductive training, based on sentence processing will be fully investigated. Comparisons with each approach to its corresponding symbolic approach will be made.

Comments

Permanent URL: http://dx.doi.org/10.7936/K7JD4V40

Recommended Citation

Faisal, Kanaan A., "CDP: A Connectionist Deterministic Parser A Dissertation Proposal" Report Number: WUCS-89-33 (1989). All Computer Science and Engineering Research.
https://openscholarship.wustl.edu/cse_research/746