Integrating top-down and bottom-up strategies in a text processing system
ANLC '88 Proceedings of the second conference on Applied natural language processing
Computational Linguistics
The GE NLToolset: a software foundation for intelligent text processing
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Creating segmented databases from free text for text retrieval
SIGIR '91 Proceedings of the 14th annual international ACM SIGIR conference on Research and development in information retrieval
Partial parsing via finite-state cascades
Natural Language Engineering
The GE NLToolset: a software foundation for intelligent text processing
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Word sense acquistion for multilingual text interpretation
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
An analogical parser for restricted domains
HLT '91 Proceedings of the workshop on Speech and Natural Language
Parsing run amok: relation-driven control for text analysis
AAAI'92 Proceedings of the tenth national conference on Artificial intelligence
Why read if you can skim: towards enabling faster screen reading
Proceedings of the International Cross-Disciplinary Conference on Web Accessibility
Accessible skimming: faster screen reading of web pages
Proceedings of the 25th annual ACM symposium on User interface software and technology
Hi-index | 0.00 |
We have designed and implemented a text processing system that can extract important information from hundreds of paragraphs per hour and can be transported within weeks to a new domain. The system performs efficiently because it determines the level of processing required to understand a text. This "skimming" method identifies surface relations in the input text that are likely to contribute to its interpretation in a domain. This approach differs from previous skimming techniques in that it uses conceptual information as part of bottom-up linguistic processing, thus using linguistic knowledge more fully while limiting grammatical complexity.