This repository contains data and code for our semantic parsing dataset SPICE. Please contact Laura Perez-Beltrachini (lperez@ed.ac.uk) or Parag Jain (parag.jain@ed.ac.uk) if you have any questions.
The dataset is available for download from here.
The scripts for the different annotations (e.g., NER/NEL) on the dataset can be found here.
Instructions on how to set up the SPICE knowledge graph can be found here.
You will find code and instructions related to our BertSP baseline here.
You will find code and instructions related to our LasagneSP baseline here.
For instructions on the evaluation scripts see here.