Learn More
We consider the task of learning a context-dependent mapping from utterances to de-notations. With only denotations at training time, we must search over a combina-torially 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(More)
Automatic program generation allows end-users to benefit from greatly from increased productivity. However, general Natural Language Programming tools fail to provide the benefits of the ambiguity and expressivity of English. We reduce program generation into a semantic parsing problem. Given a command and input , we procedurally generate a large set of(More)
  • 1