NL-EDIT: Correcting semantic parse errors through natural language interaction

03/26/2021
by   Ahmed Elgohary, et al.
0

We study semantic parsing in an interactive setting in which users correct errors with natural language feedback. We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors. We show that NL-EDIT can boost the accuracy of existing text-to-SQL parsers by up to 20 limitations of the model and discuss directions for improvement and evaluation. The code and datasets used in this paper are publicly available at http://aka.ms/NLEdit.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset