Integrated processing produces robust understanding

Authors:
Mallory Selfridge
Affiliations:
The University of Connecticut, Storrs, Connecticut
Venue:
Computational Linguistics
Year:
1986

Citing 10
Cited 2

Principles of artificial intelligence

Principles of artificial intelligence
Transition network grammars for natural language analysis

Communications of the ACM
Conceptual Information Processing

Conceptual Information Processing
A process model of language acquisition

A process model of language acquisition
Relaxation techniques for parsing grammatically III-formed input in Natural Language Understanding Systems

Computational Linguistics
Flexible parsing

Computational Linguistics
Recovery strategies for parsing extragrammatical language

Computational Linguistics - Special issue on ill-formed input
Meta-rules as a basis for processing ill-formed input

Computational Linguistics - Special issue on ill-formed input
Preference semantics, ill-formedness, and metaphor

Computational Linguistics - Special issue on ill-formed input
The NOMAD system: expectation-based detection and correction of errors during understanding of syntactically and semantically ill-formed text

Computational Linguistics - Special issue on ill-formed input

Responding to semantically ill-formed input

ANLC '88 Proceedings of the second conference on Applied natural language processing
Syntactic preferences for robust parsing with semantic preferences

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Natural language interfaces to computers must deal with wide variation in real-world input. This paper proposes that, in order to handle real-world input robustly, a natural language interface should be constructed in accord with principles of integrated processing: processing syntax and semantics at the same time, processing syntax and semantics using the same mechanisms, and processing language and memory using the same mechanisms. This paper describes an experimental natural language interface constructed according to these principles which displays the desired robustness. The success of this interface suggests that future real-world interfaces could achieve robustness by performing integrated processing.