Generative Alignment and Semantic Parsing for Learning from Ambiguous Supervision

We present a probabilistic generative model for learning semantic parsers from ambiguous supervision. Our approach learns from natural language sentences paired with world states consisting of multiple potential logical meaning representations. It disambiguates the meaning of each sentence while simultaneously learning a semantic parser that maps sentences into logical form. Compared to a previous generative model for semantic alignment, it also supports full semantic parsing. Experimental results on the Robocup sportscasting corpora in both English and Korean indicate that our approach produces more accurate semantic alignments than existing methods and also produces competitive semantic parsers and improved language generators.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Joohyun Kim, Raymond J. Mooney
• Keywords: COLING 2010, Computational Linguistics, Semantic, Semantic Alignments, Semantic Parsers