We present the first unsupervised approach for semantic parsing that rivals the accuracy of supervised approaches in translating natural-language questions to database queries. Our GUSP system produces a semantic parse by annotating the dependency-tree nodes and edges with latent states, and learns a probabilistic grammar using EM. To compensate for the lack of example annotations or question-answer pairs, GUSP adopts a novel grounded-learning approach to leverage the database content for indirect supervision. On the challenging ATIS dataset, GUSP attained an accuracy of 84%, effectively tying with the best published results by supervised approaches.
Hoifung Poon is a researcher at Microsoft Research. His research interests is in advancing machine learning and natural language processing for automating discovery in genomics and precision medicine. His most recent work focuses on scaling semantic parsing to extract biological pathways from Pubmed, and on developing probabilistic methods to incorporate pathways with high-throughput genomics data in cancer system biology. He has received Best Paper Awards in NAACL, EMNLP, and UAI.