Simpler Context-Dependent Logical Forms via Model Projections

Understand

We consider the task of learning a context-dependent mapping from utterances to denotations.

• With only denotations at training time, we must search over a combinatorially large space of logical forms, which is even larger with context-dependent utterances.
• To cope with this challenge, we perform successive projections of the full model onto simpler models that operate over equivalence classes of logical forms.
• Though less expressive, we find that these simpler models are much faster and can be surprisingly effective.