Semantic Parsing Freebase: Towards Open-domain Semantic Parsing

Existing semantic parsing research has steadily improved accuracy on a few domains and their corresponding databases. This paper introduces FreeParser, a system that trains on one domain and one set of predicate and constant symbols, and then can parse sentences for any new domain, including sentences that refer to symbols never seen during training. FreeParser uses a domain-independent architecture to automatically identify sentences relevant to each new database symbol, which it uses to supplement its manually-annotated training data from the training domain. In cross-domain experiments involving 23 domains, FreeParser can parse sentences for which it has seen comparable unannotated sentences with an F1 of 0.71.