The KERNEL text understanding system
Artificial Intelligence - Special volume on natural language processing
Empirical methods for artificial intelligence
Empirical methods for artificial intelligence
SPARKLE Work Package 1: Specification of Phrasal Parsing. Final Report
SPARKLE Work Package 1: Specification of Phrasal Parsing. Final Report
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
A trainable rule-based algorithm for word segmentation
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Word sense disambiguation using optimised combinations of knowledge sources
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Classifier combination for improved lexical disambiguation
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Improving data driven wordclass tagging by system combination
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
A rule-based approach to prepositional phrase attachment disambiguation
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Supervised grammar induction using training data with limited constituent information
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
High precision extraction of grammatical relations
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
High precision extraction of grammatical relations
New developments in parsing technology
Hi-index | 0.00 |
Grammatical relationships (GRs) form an important level of natural language processing, but different sets of GRs are useful for different purposes. Therefore, one may often only have time to obtain a small training corpus with the desired GR annotations. To boost the performance from using such a small training corpus on a transformation rule learner, we use existing systems that find related types of annotations.