A statistical approach to machine translation
Computational Linguistics
A template matcher for robust NL interpretation
HLT '91 Proceedings of the workshop on Speech and Natural Language
Fundamentals of speech recognition
Fundamentals of speech recognition
The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Robust processing of real-world natural-language texts
ANLC '92 Proceedings of the third conference on Applied natural language processing
An efficient chart-based algorithm for partial-parsing of unrestricted texts
ANLC '92 Proceedings of the third conference on Applied natural language processing
Some chart-based techniques for parsing ill-formed input
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
An integrated heuristic scheme for partial parse evaluation
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Multi-lingual translation of spontaneously spoken language in a limited domain
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
A relaxation method for understanding spontaneous speech utterances
HLT '91 Proceedings of the workshop on Speech and Natural Language
The Semantic Linker: a new fragment combining method
HLT '93 Proceedings of the workshop on Human Language Technology
Pattern matching in a linguistically-motivated text understanding system
HLT '94 Proceedings of the workshop on Human Language Technology
Filling knowledge gaps in a broad coverage machine translation system
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
Real-world natural language sentences are often long and complex, and contain unexpected grammatical constructions. They even include noiseand ungrammaticality. This paper describes the Controlled SkipParser, a program that parses such real-world sentences by skippingsome of the words in the sentence. The new feature of this parser is that itcontrols its behavior by finding out which words to skip, without usingdomain-specific knowledge. The parser is a priority-based chartparser. By assigning appropriate priority levels to the constituentsin the chart, the parser‘s behavior is controlled. Statisticalinformation is used for assigning priority levels. The statisticalinformation (n-grams) can be thought of as a generalized approximationof the grammar learned from past successful experiences. The controlmechanism gives a great speed-up and reduction in memory usage. Experiments on real newspaper articles are shown, and our experiencewith this parser in a machine translation system is described.