# Semantic Parsing to Probabilistic Programs for Situated Question Answering

Source: [Semantic Parsing to Probabilistic Programs for Situated Question Answering](<https://www.sota2.com/research/paper/68fa62bc1e209131ce9faf63>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:25:18.953Z

Authors: Jayant Krishnamurthy, Oyvind Tafjord, Aniruddha Kembhavi

Published: 2016-06-22T19:19:29.000Z

## Abstract

Situated question answering is the problem of answering questions about an environment such as an image or diagram. This problem requires jointly interpreting a question and an environment using background knowledge to select the correct answer. We present Parsing to Probabilistic Programs (P3), a novel situated question answering model that can use background knowledge and global features of the question/environment interpretation while retaining efficient approximate inference. Our key insight is to treat semantic parses as probabilistic programs that execute nondeterministically and whose possible executions represent environmental uncertainty. We evaluate our approach on a new, publicly-released data set of 5000 science diagram questions, outperforming several competitive classical and neural baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1606.07046>)

[PDF](<https://arxiv.org/pdf/1606.07046.pdf>)