Semantic Parsing to Probabilistic Programs for Situated Question Answering

@article{Krishnamurthy2016SemanticPT,
  title={Semantic Parsing to Probabilistic Programs for Situated Question Answering},
  author={Jayant Krishnamurthy and Oyvind Tafjord and Aniruddha Kembhavi},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.07046}
}
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… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 16 CITATIONS

Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Probabilistic Neural Programs

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Probabilistic Neural Programs

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND

Towards Literate Artificial Intelligence

VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Parsing to Programs: A Framework for Situated QA

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 29 REFERENCES

VQA: Visual Question Answering

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Toward understanding natural language directions

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A Diagram is Worth a Dozen Images

VIEW 3 EXCERPTS

2016a. Deep compositional question answering with neural module

  • Marcus Rohrbach, Trevor Darrell, Dan Klein
  • 2016

Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images

VIEW 1 EXCERPT

Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary

VIEW 1 EXCERPT