The nature of statistical learning theory
The nature of statistical learning theory
A maximum entropy approach to natural language processing
Computational Linguistics
Head-driven statistical models for natural language parsing
Head-driven statistical models for natural language parsing
Support Vector Learning for Semantic Argument Classification
Machine Learning
FrameNet-based semantic parsing using maximum entropy models
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Automatic semantic role labeling for Chinese verbs
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Introduction to the CoNLL-2005 shared task: semantic role labeling
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
A hybrid convolution tree kernel for semantic role labeling
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Labeling chinese predicates with semantic roles
Computational Linguistics
Using a Hybrid Convolution Tree Kernel for Semantic Role Labeling
ACM Transactions on Asian Language Information Processing (TALIP)
Semantic parsing for high-precision semantic role labelling
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
A cascaded syntactic and semantic dependency parsing system
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Probabilistic model for syntactic and semantic dependency parsing
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Parsing syntactic and semantic dependencies for multiple languages with a pipeline approach
CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Introduction to the CoNLL-2005 shared task: semantic role labeling
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
| Hi-index | 0.00 |
A maximum entropy classifier is used in our semantic role labeling system, which takes syntactic constituents as the labeling units. The maximum entropy classifier is trained to identify and classify the predicates' semantic arguments together. Only the constituents with the largest probability among embedding ones are kept. After predicting all arguments which have matching constituents in full parsing trees, a simple rule-based post-processing is applied to correct the arguments which have no matching constituents in these trees. Some useful features and their combinations are evaluated.