Foodwebs

Aristo • 2016
The foodwebs dataset contains 5000 questions about 500 food web diagrams. Each diagram has annotations from a computer vision system and each question is annotated with a logical form.

Paper Appendix

The paper appendix describes the semantic parser and execution model’s features:

Appendix: Semantic Parsing to Probabilistic Programs forSituated Question Answering

Code

An implementation of Parsing to Probabilistic Programs (P3) is available as part of jklol.

See the instructions for running the SCENE experiment.