학술논문
Hidden understanding models for statistical sentence understanding
Document Type
Conference
Author
Source
1997 IEEE International Conference on Acoustics, Speech, and Signal Processing Acoustics, speech, and signal processing Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on. 2:1479-1482 vol.2 1997
Subject
Language
ISSN
1520-6149
Abstract
We describe the first sentence understanding system that is completely based on learned methods both for understanding individual sentences, and determining their meaning in the context of preceding sentences. We divide the problem into three stages: semantic parsing, semantic classification, and discourse modeling. Each of these stages requires a different model. When we ran this system on the last test (December, 1994) of the ARPA Air Travel Information System (ATIS) task, we achieved a 13.7% error rate. The error rate for those sentences that are context-independent (class A) was 9.7%.