Paper: Learning to Map Text to Graph-Based Meaning Representations via Grammar Induction

ACL ID W08-2002
Title Learning to Map Text to Graph-Based Meaning Representations via Grammar Induction
Venue Coling 2008: Proceedings of the workshop on Speech Processing for Safety Critical Translation and Pervasive Applications
Session
Year 2008
Authors

We argue in favor of using a graph-based representation for language meaning and propose a novel learning method to map natural language text to its graph-based meaning representation. We present a grammar formalism, which combines syn- tax and semantics, and has ontology con- straints at the rule level. These constraints establish links between language expres- sions and the entities they refer to in the real world. We present a relational learning algorithm that learns these grammars from a small representative set of annotated ex- amples, and show how this grammar in- duction framework and the ontology-based semantic representation allow us to di- rectly map text to graph-based meaning representations.