Semantic Parsing to Probabilistic Programs for Situated Question Answering [article]

Jayant Krishnamurthy and Oyvind Tafjord and Aniruddha Kembhavi
2016 arXiv   pre-print
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
more » ... 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.
arXiv:1606.07046v2 fatcat:cxv57nce3zbxlg4sjz6zhwssxe