AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data

10/09/2020 ∙ by Silei Xu, et al. ∙ 15

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 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 16.4 than the same model trained with human data.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

Code Repositories

genienlp

This repository contains the code for Genie NLP models


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.