How to Evaluate Controlled Natural Languages
Human-Computer Interaction
2009-07-08 v1
Abstract
This paper presents a general framework how controlled natural languages can be evaluated and compared on the basis of user experiments. The subjects are asked to classify given statements (in the language to be tested) as either true or false with respect to a certain situation that is shown in a graphical notation called "ontographs". A first experiment has been conducted that applies this framework to the language Attempto Controlled English (ACE).
Keywords
Cite
@article{arxiv.0907.1251,
title = {How to Evaluate Controlled Natural Languages},
author = {Tobias Kuhn},
journal= {arXiv preprint arXiv:0907.1251},
year = {2009}
}