A shortest path dependency kernel for relation extraction
R. Bunescu, und R. Mooney. Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, Seite 724--731. Stroudsburg, PA, USA, Association for Computational Linguistics, (2005)
DOI: 10.3115/1220575.1220666
Zusammenfassung
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.
Beschreibung
A shortest path dependency kernel for relation extraction
%0 Conference Paper
%1 bunescu2005shortest
%A Bunescu, Razvan C.
%A Mooney, Raymond J.
%B Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
%C Stroudsburg, PA, USA
%D 2005
%I Association for Computational Linguistics
%K dependency extraction kernel path relation shortest
%P 724--731
%R 10.3115/1220575.1220666
%T A shortest path dependency kernel for relation extraction
%U http://dx.doi.org/10.3115/1220575.1220666
%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{bunescu2005shortest,
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.},
acmid = {1220666},
added-at = {2012-11-02T22:05:53.000+0100},
address = {Stroudsburg, PA, USA},
author = {Bunescu, Razvan C. and Mooney, Raymond J.},
biburl = {https://www.bibsonomy.org/bibtex/2a138a177aead97946bdee2777f98a3f8/jil},
booktitle = {Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing},
description = {A shortest path dependency kernel for relation extraction},
doi = {10.3115/1220575.1220666},
interhash = {f1bcae1ef528ab148f9e31e94a6fe6a2},
intrahash = {a138a177aead97946bdee2777f98a3f8},
keywords = {dependency extraction kernel path relation shortest},
location = {Vancouver, British Columbia, Canada},
numpages = {8},
pages = {724--731},
publisher = {Association for Computational Linguistics},
series = {HLT '05},
timestamp = {2013-11-23T20:11:51.000+0100},
title = {A shortest path dependency kernel for relation extraction},
url = {http://dx.doi.org/10.3115/1220575.1220666},
year = 2005
}