Date of Award

2015

Document Type

Thesis

Department

Mathematics

First Reader

Dr. Jeff Matocha

Second Reader

Dr. Joey Dodson

Third Reader

Dr. Darin Buscher

Abstract

This research presents novel algorithms which generate sentences in a natural language, using natural language generation techniques. The purpose of the algorithms is to benefit foreign language learning. As far as we can tell, ours is the first such research being done in the field. In creating the algorithms, we also developed a piece of software to showcase the work and allow testing by users. The main algorithm begins by generating sentence models by using one of two methods, namely modeled sentence generation and semantic sentence generation. Each of these have benefits and drawbacks, which the user must take into consideration when generating sentences. When the models are generated, they are filled in word by word using a conjugation algorithm. The completed sentences are then returned to the user and may then be translated. There is still much work to do before we will be satisfied with the algorithms, but our research shows that it is possible to use natural language generation techniques to benefit foreign language learning.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.