Language understanding using hidden understanding models

Author

Schwartz, Richard ; Miller, Scott ; Stallard, David ; Makhoul, John

Author_Institution

BBN Syst. & Technol. Corp., Cambridge, MA, USA

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

997

Abstract

Describes a sentence understanding system that is completely based on learned methods both for understanding individual sentences and for determining their meaning in the context of the 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 December 1994 test of the ARPA Air Travel Information System (ATIS) task, we achieved a 14.5% error rate. The error rate for those sentences that are context-independent (class A) was 9.5%

Keywords

natural languages; pattern classification; public information systems; speech recognition; travel industry; ARPA Air Travel Information System; ATIS task; class A sentences; context-independent sentences; discourse modeling; error rate; hidden understanding models; language understanding; learned methods; semantic classification; semantic parsing; sentence meaning determination; sentence understanding system; Error analysis; Hidden Markov models; Information systems; Natural languages; Probability; Radio access networks; Robustness; Speech recognition; System testing; Tagging;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607771

Filename

607771