Learning to Map Context-Dependent Sentences to Executable Formal Queries

Understand

We propose a context-dependent model to map utterances within an interaction to executable formal queries.

• To incorporate interaction history, the model maintains an interaction-level encoder that updates after each turn, and can copy sub-sequences of previously predicted queries during generation.
• Our approach combines implicit and explicit modeling of references between utterances.
• We evaluate our model on the ATIS flight planning interactions, and demonstrate the benefits of modeling context and explicit references.