Conceptual structures: information processing in mind and machine
Conceptual structures: information processing in mind and machine
TINA: a natural language system for spoken language applications
Computational Linguistics
Stochastically-Based Semantic Analysis
Stochastically-Based Semantic Analysis
Some uses of higher-order logic in computational linguistics
ACL '86 Proceedings of the 24th annual meeting on Association for Computational Linguistics
Parsing spoken language without syntax
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Hi-index | 0.00 |
In Human-Computer dialogue, spoken language understanding systems use mainly selective methods and are limited to very specific domains. On the contrary we present in this paper a speech understanding system which achieves a more detailed analysis of spoken recognized utterances.The semantic representation of a sentence is a logic formula. Semantic and pragmatic considerations shape the formula. The analysis itself is split into two phases based on different principles. The first phase is almost exclusively syntactic. It corresponds to a segmentation into chunks whose meaning is obtained by composing 驴-terms to build elementary formulas. In the second phase, the chunks are interpreted and then composed, mainly through coordination. These compositions are mainly based on pragmatic contraints provided most of the time by the context of the application.We give here an account of the results obtained from a first series of tests. We also discuss the use of the same ideas for applications in well defined semantic domains such as database processing.