Semantic role labeling via instance-based learning
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
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 |
This paper describes a system for semantic role labeling for the CoNLL2005 Shared task. We divide the task into two sub-tasks: boundary recognition by a general tree-based predicate-argument recognition algorithm to convert a parse tree into a flat representation of all predicates and their related boundaries, and role labeling by a consensus model using a pattern-matching framework to find suitable roles for core constituents and adjuncts. We describe the system architecture and report results for the CoNLL2005 development dataset.