Using predicate-argument structures for information extraction
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Optimal constituent alignment with edge covers for semantic projection
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Question answering based on semantic structures
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
The second release of the RASP system
COLING-ACL '06 Proceedings of the COLING/ACL on Interactive presentation sessions
A FrameNet-based semantic role labeler for Swedish
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
LIBLINEAR: A Library for Large Linear Classification
The Journal of Machine Learning Research
The effect of syntactic representation on semantic role labeling
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Semi-supervised semantic role labeling
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Automatic induction of FrameNet lexical units
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
SemEval'07 task 19: frame semantic structure extraction
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Unsupervised induction of semantic roles
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Towards open-domain Semantic Role Labeling
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Open-domain semantic role labeling by modeling word spans
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
A structured model for joint learning of argument roles and predicate senses
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Evaluating FrameNet-style semantic parsing: the role of coverage gaps in FrameNet
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Unsupervised semantic role induction via split-merge clustering
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
A Bayesian model for unsupervised semantic parsing
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Structured lexical similarity via convolution kernels on dependency trees
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Unsupervised semantic role induction with graph partitioning
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Towards semi-supervised brazilian portuguese semantic role labeling: building a benchmark
PROPOR'12 Proceedings of the 10th international conference on Computational Processing of the Portuguese Language
A Bayesian approach to unsupervised semantic role induction
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Unsupervised induction of frame-semantic representations
WILS '12 Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure
Crosslingual induction of semantic roles
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Hi-index | 0.00 |
Unknown lexical items present a major obstacle to the development of broad-coverage semantic role labeling systems. We address this problem with a semi-supervised learning approach which acquires training instances for unseen verbs from an unlabeled corpus. Our method relies on the hypothesis that unknown lexical items will be structurally and semantically similar to known items for which annotations are available. Accordingly, we represent known and unknown sentences as graphs, formalize the search for the most similar verb as a graph alignment problem and solve the optimization using integer linear programming. Experimental results show that role labeling performance for unknown lexical items improves with training data produced automatically by our method.