Building or learning semantic parsers has been an interesting approach for creating natural language interfaces (NLI's) for databases. Recently, the problem of imperfect precision in an NLI has been brought up as an NLI that might answer a question incorrectly can render it unstable, if not useless. In this paper, an approach based on ensemble learning is proposed to trivially address the problem of unreliability in an NLI due to imperfect precision in the semantic parser in a way that also allows the recall of the NLI to be improved. Experimental results in two real world domains suggested that such an approach can be promising.
展开▼