Partial parsing: a report on work in progress
HLT '91 Proceedings of the workshop on Speech and Natural Language
Finite-state approximations of grammars
HLT '90 Proceedings of the workshop on Speech and Natural Language
The generic information extraction system
MUC5 '93 Proceedings of the 5th conference on Message understanding
GE-CMU: description of the SHOGUN system used for MUC-5
MUC5 '93 Proceedings of the 5th conference on Message understanding
New York University: description of the Proteus system as used for MUC-5
MUC5 '93 Proceedings of the 5th conference on Message understanding
UMass/Hughes: description of the CIRCUS system used for MUC-5
MUC5 '93 Proceedings of the 5th conference on Message understanding
Machine Translation
| Hi-index | 0.00 |
An ongoing debate in text understanding efforts centers on the use of pattern-matching techniques, which some have characterized as "designed to ignore as much text as possible," versus approaches which primarily employ rules that are domain-independent and linguistically-motivated. For instance, in the message-processing community, there has been a noticeable pulling back from large-coverage grammars to the point where, in some systems, traditional models of syntax and semantics have been completely replaced by domain-specific finite-state approximations.In this paper we report on a hybrid approach which uses such domain-specific patterns as a supplement to domain-independent grammar rules, domain-independent semantic rules, and automatically hypothesized domain-specific semantic rules. The surprising result, as measured on TIPSTER test data, is that domain-specific pattern matching improved performance, but only slightly, over more general linguistically-motivated techniques.