Schema2QA
material
ID: schema2qa
Related Papers
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
AbstractWe propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. Given a database schema and its data, AutoQA automatically generates …...
Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization
AbstractModern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have …...