We present a novel approach to relation extraction, based on the observation that the information required to assert a relationship between two named entities in the same sentence is typically captured by the shortest path between the two entities in the dependency graph. Experiments on extracting top-level relations from the ACE (Automated Content Extraction) newspaper corpus show that the new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels.

PDF, PS

In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05), pp. 724-731, Vancouver, BC, October 2005.

@inproceedings{bunescu:emnlp05, title={A Shortest Path Dependency Kernel for Relation Extraction}, author={R. C. Bunescu and Raymond J. Mooney}, booktitle={Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05)}, month={October}, address={Vancouver, BC}, pages={724-731}, url="http://www.cs.utexas.edu/users/ai-lab?bunescu:emnlp05", year={2005} }