Paper: Learning Context-Dependent Mappings from Sentences to Logical Form

ACL ID P09-1110
Title Learning Context-Dependent Mappings from Sentences to Logical Form
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

We consider the problem of learning context-dependent mappings from sen- tences to logical form. The training ex- amples are sequences of sentences anno- tated with lambda-calculus meaning rep- resentations. Wedevelopanalgorithmthat maintains explicit, lambda-calculus repre- sentations of salient discourse entities and uses a context-dependent analysis pipeline to recover logical forms. The method uses a hidden-variable variant of the percep- tion algorithm to learn a linear model used to select the best analysis. Experiments on context-dependent utterances from the ATIS corpus show that the method recov- ers fully correct logical forms with 83.7% accuracy.