SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.14540 · NAACL · 2021

NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction

Ahmed Awadallah, Christopher Meek, Ahmed Elgohary, Adam Fourney, Matthew Richardson, Gonzalo Ramos

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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% with only one round of correction. We analyze the 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.14540")
get_code_for_paper("2103.14540")
have("2103.14540")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.14540.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.14540.svg)](https://syntology.ai/paper/2103.14540)

Connect an agent — have() is free.