Semantic Parsing to Probabilistic Programs for Situated Question Answering

Jayant Krishnamurthy, Oyvind Tafjord, Aniruddha Kembhavi
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
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 3 ), 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 » ... ht 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.
doi:10.18653/v1/d16-1016 dblp:conf/emnlp/KrishnamurthyTK16 fatcat:6gpv54mocvf43fuuffh27fm4he