One-on-one tutoring is a particularly effective mode of instruction, a
nd we have studied the behavior of expert tutors in such a setting. A
tactic commonly used by our expert tutors is hinting, that is, the pro
mpting of a student to recollect information presumed to be known to h
im or her, or the prompting of a student to make an inference needed t
o solve a problem or answer a question, or both. Hints may directly co
nvey information or may point to information the student already posse
sses. Another tactic prompts the student in a step-by-step manner (in
a directed line of reasoning) to an answer. Our tutors generated 315 h
ints and directed lines of reasoning in 30 hr of tutoring. The surface
structure of hints is complex and varied, reflecting, in part, the fa
ct that the utterances making up hints often serve multiple functions.
Hinting is triggered by student errors but ceases when it appears tha
t the student is unable to respond appropriately. Hints encourage the
student to engage in active cognitive processes that are thought to pr
omote deeper understanding and long-term retention. It is our intentio
n to apply our knowledge of tutorial dialogue generation to the buildi
ng of an intelligent tutoring system (ITS).