Allen Institute for AI


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


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

See the instructions for running the SCENE experiment.