A Shortest Path Dependency Kernel for Relation Extraction
R. Bunescu, and R. Mooney. Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, page 724--731. Vancouver, British Columbia, Canada, Association for Computational Linguistics, (October 2005)
Abstract
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.
%0 Conference Paper
%1 Bunescu:Mooney:05
%A Bunescu, Razvan
%A Mooney, Raymond
%B Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing
%C Vancouver, British Columbia, Canada
%D 2005
%I Association for Computational Linguistics
%K graphs kernels structure 2005 emnlp
%P 724--731
%T A Shortest Path Dependency Kernel for Relation Extraction
%U http://acl.ldc.upenn.edu/H/H05/H05-1091.pdf
%X 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.
@inproceedings{Bunescu:Mooney:05,
abstract = {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.},
added-at = {2007-01-29T18:58:52.000+0100},
address = {Vancouver, British Columbia, Canada},
author = {Bunescu, Razvan and Mooney, Raymond},
biburl = {https://www.bibsonomy.org/bibtex/26548b6e9e35809bd06003bc51419d2f9/seandalai},
booktitle = {Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing},
interhash = {f1bcae1ef528ab148f9e31e94a6fe6a2},
intrahash = {6548b6e9e35809bd06003bc51419d2f9},
keywords = {graphs kernels structure 2005 emnlp},
month = {October},
pages = {724--731},
publisher = {Association for Computational Linguistics},
timestamp = {2007-01-29T18:58:52.000+0100},
title = {A Shortest Path Dependency Kernel for Relation Extraction},
url = {http://acl.ldc.upenn.edu/H/H05/H05-1091.pdf},
year = 2005
}