This page contains supplementary material and data for the paper: Semantic Parsing to Probabilistic Programs for Situated Question Answering (EMNLP 2016).
Foodwebs Data set
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. The data set may be downloaded here (200 MB).
The paper appendix describes the semantic parser and execution model's features. PDF
An implementation of Parsing to Probabilistic Programs (P3) is available as part of jklol. Instructions for running the SCENE experiment are available here. Code for the food web experiment will be available soon.