SCISOR: extracting information from on-line news
Communications of the ACM
Generating a grammar for statistical training
HLT '90 Proceedings of the workshop on Speech and Natural Language
Generic text processing: a progress report
HLT '90 Proceedings of the workshop on Speech and Natural Language
An evaluation of text analysis technologies
AI Magazine
Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems
Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems
A news story categorization system
ANLC '88 Proceedings of the second conference on Applied natural language processing
Integrating top-down and bottom-up strategies in a text processing system
ANLC '88 Proceedings of the second conference on Applied natural language processing
Joining statistics with NLP for text categorization
ANLC '92 Proceedings of the third conference on Applied natural language processing
The GE NLToolset: a software foundation for intelligent text processing
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
To parse or not to parse: relation-driven text skimming
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 2
Comparing MUCK-II and MUC-3: assessing the difficulty of different tasks
MUC3 '91 Proceedings of the 3rd conference on Message understanding
GE NLTooLSET: MUC-3 test results and analysis
MUC3 '91 Proceedings of the 3rd conference on Message understanding
GE: description of the NLTooLSET system as used for MUC-3
MUC3 '91 Proceedings of the 3rd conference on Message understanding
| Hi-index | 0.00 |
Traditional syntactic models of parsing have been inadequate for task-driven processing of extended text, because they spend most of their time on misdirected linguistic analysis, leading to problems with both efficiency and coverage. Statistical and domain-driven processing offer compelling possibilities, but only as a complement to syntactic processing. For semanticallyoriented tasks such as data extraction from text, the problem is how to combine the coverage of these "weaker" methods with the detail and accuracy of traditional lingusitic analysis. A good approach is to focus linguistic analysis on relations that directly impact the semantic results, detaching these relations from the complete constituents to which they belong. This approach results in a faster, more robust, and potentially more accurate parser for real text.