AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
This enables automated QA system creation for databases without manual annotation, though it is incremental over existing synthetic data methods.
AutoQA automatically generates semantic parsers for question answering on databases using only synthetic training data, achieving 62.9% logical form accuracy on Schema2QA (6.4% below human-annotated models) and 69.8% answer accuracy on Overnight (16.4% above zero-shot SOTA).
We 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 a large set of high-quality questions for training that covers different database operations. It uses automatic paraphrasing combined with template-based parsing to find alternative expressions of an attribute in different parts of speech. It also uses a novel filtered auto-paraphraser to generate correct paraphrases of entire sentences. We apply AutoQA to the Schema2QA dataset and obtain an average logical form accuracy of 62.9% when tested on natural questions, which is only 6.4% lower than a model trained with expert natural language annotations and paraphrase data collected from crowdworkers. To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset. AutoQA achieves 69.8% answer accuracy, 16.4% higher than the state-of-the-art zero-shot models and only 5.2% lower than the same model trained with human data.