Language understanding using hidden understanding models

We describe the first sentence understanding system that is completely based on learned methods both for understanding individual sentences, and determinig their meaning in the context of preceding sentences. We describe the models used for each of three stages in the understanding: semantic parsing, semantic classification, and discourse modeling. When we ran this system on the last test (December, 1994) of the ARPA Air Travel Information System (ATIS) task, we achieved 14.5% error rate. The error rate for those sentences that are context-independent (class A) was 9.5%.