Automatic labeling of semantic roles
Computational Linguistics
Joint learning improves semantic role labeling
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
LIBLINEAR: A Library for Large Linear Classification
The Journal of Machine Learning Research
Adding semantic roles to the chinese treebank
Natural Language Engineering
The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Dependency-based syntactic-semantic analysis with PropBank and NomBank
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
The CoNLL-2009 shared task: syntactic and semantic dependencies in multiple languages
CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
A structured model for joint learning of argument roles and predicate senses
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
A high-performance syntactic and semantic dependency parser
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations
Analysis of the difficulties in Chinese deep parsing
IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies
Mining semantics for culturomics: towards a knowledge-based approach
Proceedings of the 2013 international workshop on Mining unstructured big data using natural language processing
| Hi-index | 0.00 |
This paper describes our contribution to the semantic role labeling task (SRL-only) of the CoNLL-2009 shared task in the closed challenge (Hajič et al., 2009). Our system consists of a pipeline of independent, local classifiers that identify the predicate sense, the arguments of the predicates, and the argument labels. Using these local models, we carried out a beam search to generate a pool of candidates. We then reranked the candidates using a joint learning approach that combines the local models and proposition features. To address the multilingual nature of the data, we implemented a feature selection procedure that systematically explored the feature space, yielding significant gains over a standard set of features. Our system achieved the second best semantic score overall with an average labeled semantic F1 of 80.31. It obtained the best F1 score on the Chinese and German data and the second best one on English.