Centering: a framework for modeling the local coherence of discourse
Computational Linguistics
Efficient parsing for Korean and English: a parameterized message-passing approach
Computational Linguistics
Computational Linguistics
Principle-based parsing without overgeneration
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
PRINCIPAR: an efficient, broad-coverage, principle-based parser
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
University of Manitoba: description of the NUBA system as used for MUC-5
MUC5 '93 Proceedings of the 5th conference on Message understanding
A Comparative Study of Information Extraction Strategies
CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
Evaluation-driven design of a robust coreference resolution system
Natural Language Engineering
Using a semantic network for information extraction
Natural Language Engineering
Reference resolution beyond coreference: a conceptual frame and its application
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Improving machine learning approaches to coreference resolution
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Adaptive information extraction
ACM Computing Surveys (CSUR)
Characterizing stylistic elements in syntactic structure
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
| Hi-index | 0.00 |
The PIE (Principar-driven Information Extraction) system takes a different approach to the problem of information extraction from the NUBA system that was used in MUC-5. The NUBA system did not have a parser and relies on an abductive reasoner to construct the semantic relationships between domain specific concepts mentioned in a sentence. The PIE system, on the other hand, relies heavily on a principle-based broad-coverage parser, called PRINCIPAR [2, 6, 8], that we have developed over the past three years. Most of the information extracted are directly "read-off" the parser outputs by a subtree pattern-matcher, bypassing the usual step of constructing semantic representations.