PRECISE on ATIS: semantic tractability and experimental results
Ana-Maria Popescu, Alex Armanasu, Oren Etzioni, David Ko, Alexander Yates · 2004
The need for Natural Language Interfaces to databases (NLIs) has become increasingly acute as more and more people ac-cess information through their web browsers, PDAs, and cell phones. Yet NLIs are only usable if they map natural lan-guage questions to SQL queries correctly — people are un-willing to trade reliable and predictable user interfaces for intelligent but unreliable ones. We describe a reliable NLI, PRECISE, that incorporates a modern statistical paser and a semantic module. PRECISE provably handles a large class of natural language questions correctly. On the benchmark ATIS data set, PRECISE achieves 93.8 % accuracy.