Paper: Deterministic Statistical Mapping of Sentences to Underspecified Semantics

ACL ID W11-0103
Title Deterministic Statistical Mapping of Sentences to Underspecified Semantics
Venue IWCS
Session Main Conference
Year 2011
Authors

We present a method for training a statistical model for mapping natural language sentences to semantic expressions. The semantics are expressions of an underspecified logical form that has prop- erties making it particularly suitable for statistical mapping from text. An encoding of the semantic expressions into dependency trees with automatically generated labels allows application of exist- ing methods for statistical dependency parsing to the mapping task (without the need for separate traditional dependency labels or parts of speech). The encoding also results in a natural per-word semantic-mapping accuracy measure. We report on the results of training and testing statistical mod- els for mapping sentences of the Penn Treebank into the semantic expressions, for which per-word semantic...