Abstract

A study of the use of and and or for specifying intersection and union relationships between conjoined qualifiers of varying characteristics was conducted using a simulated natural language query system. Subjects always used or correctly to indicate union but and was used to indicate both union and intersection. Interpretation rules were defined that could be used to clarify the intended meaning for and for some but not all of the cases. The results indicated subjects could implicitly learn to be more precise. These results suggest that natural language interfaces can be built to recognize ambiguous input and should prompt users for clarification. Simple syntactic elements that would distinguish the meaning of and can be defined and taught to users.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call