Learning Language Semantics from Ambiguous Supervision

Rohit J. Kate, Raymond J. Mooney

This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of natural language sentences annotated with multiple potential meaning representations, only one of which is correct. Such ambiguous supervision models the type of supervision that can be more naturally available to language-learning systems. Given such weak supervision, our approach produces a semantic parser that maps sentences into meaning representations. An existing semantic parsing learning system that can only learn from unambiguous supervision is augmented to handle ambiguous supervision. Experimental results show that the resulting system is able to cope up with ambiguities and learn accurate semantic parsers.

Subjects: 13. Natural Language Processing; 12. Machine Learning and Discovery

Submitted: Apr 11, 2007

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.