Next: Method
Up: Baseline model performance
Previous: Baseline model performance
I made use of four human
evaluators in my study. Two were
high-school English teachers with many years of experience
dealing with the teaching of literature, including short stories.
One evaluator was a
computer science professor with a research
background in natural language processing.
The final evaluator was a research scientist
with a background in linguistics and teaching
English as a second language.
Kenneth Moorman
11/4/1997