Learning from Ambiguous Examples

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 12

Student Abstracts

Current inductive learning systems are not well suited to learning from ambiguous examples. We say that an example is ambiguous if it has multiple interpretations, only one of which may be valid. Some domains in which ambiguous learning problems can be found are natural language processing (NLP) and computer vision. An example of an ambiguous training instance with two interpretations is shown below, where @ is the Exclusive-OR function and each interpretation is a conjunction of attribute values.