Semantic Parsing to Probabilistic Programs for Situated Question Answering

@inproceedings{Krishnamurthy2016SemanticPT,
  title={Semantic Parsing to Probabilistic Programs for Situated Question Answering},
  author={Jayant Krishnamurthy and Oyvind Tafjord and Aniruddha Kembhavi},
  booktitle={EMNLP},
  year={2016}
}
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 (P ), 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

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

2016a. Deep compositional question answering with neural module

  • Marcus Rohrbach, Trevor Darrell, Dan Klein
  • 2016

Similar Papers

Loading similar papers…