ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1606.07046
67
25
v1v2 (latest)

Semantic Parsing to Probabilistic Programs for Situated Question Answering

22 June 2016
Jayant Krishnamurthy
Oyvind Tafjord
ArXiv (abs)PDFHTML
Abstract

Situated question answering is the problem of answering questions about an environment such as an image. This problem requires interpreting both a question and the environment, and is challenging because the set of interpretations is large, typically superexponential in the number of environmental objects. Existing models handle this challenge by making strong -- and untrue -- independence assumptions. We present Parsing to Probabilistic Programs (P3), a novel situated question answering model that utilizes approximate inference to eliminate these independence assumptions and enable the use of global features of the question/environment interpretation. 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, finding that our approach outperforms several competitive baselines.

View on arXiv
Comments on this paper