PATTY: A Taxonomy of Relational Patterns with Semantic Types
N. Nakashole, G. Weikum, and F. Suchanek. Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, page 1135--1145. Stroudsburg, PA, USA, Association for Computational Linguistics, (2012)
Abstract
This paper presents PATTY: a large resource for textual patterns that denote binary relations between entities. The patterns are semantically typed and organized into a subsumption taxonomy. The PATTY system is based on efficient algorithms for frequent itemset mining and can process Web-scale corpora. It harnesses the rich type system and entity population of large knowledge bases. The PATTY taxonomy comprises 350,569 pattern synsets. Random-sampling-based evaluation shows a pattern accuracy of 84.7%. PATTY has 8,162 subsumptions, with a random-sampling-based precision of 75%. The PATTY resource is freely available for interactive access and download.
%0 Conference Paper
%1 Nakashole:2012:PTR:2390948.2391076
%A Nakashole, Ndapandula
%A Weikum, Gerhard
%A Suchanek, Fabian
%B Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
%C Stroudsburg, PA, USA
%D 2012
%I Association for Computational Linguistics
%K pattern relation semantic taxonomy
%P 1135--1145
%T PATTY: A Taxonomy of Relational Patterns with Semantic Types
%U http://dl.acm.org/citation.cfm?id=2390948.2391076
%X This paper presents PATTY: a large resource for textual patterns that denote binary relations between entities. The patterns are semantically typed and organized into a subsumption taxonomy. The PATTY system is based on efficient algorithms for frequent itemset mining and can process Web-scale corpora. It harnesses the rich type system and entity population of large knowledge bases. The PATTY taxonomy comprises 350,569 pattern synsets. Random-sampling-based evaluation shows a pattern accuracy of 84.7%. PATTY has 8,162 subsumptions, with a random-sampling-based precision of 75%. The PATTY resource is freely available for interactive access and download.
@inproceedings{Nakashole:2012:PTR:2390948.2391076,
abstract = {This paper presents PATTY: a large resource for textual patterns that denote binary relations between entities. The patterns are semantically typed and organized into a subsumption taxonomy. The PATTY system is based on efficient algorithms for frequent itemset mining and can process Web-scale corpora. It harnesses the rich type system and entity population of large knowledge bases. The PATTY taxonomy comprises 350,569 pattern synsets. Random-sampling-based evaluation shows a pattern accuracy of 84.7%. PATTY has 8,162 subsumptions, with a random-sampling-based precision of 75%. The PATTY resource is freely available for interactive access and download.},
acmid = {2391076},
added-at = {2016-07-16T17:05:43.000+0200},
address = {Stroudsburg, PA, USA},
author = {Nakashole, Ndapandula and Weikum, Gerhard and Suchanek, Fabian},
biburl = {https://www.bibsonomy.org/bibtex/26c13206fbc5b5dc07fb61901e2805ed4/hotho},
booktitle = {Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning},
interhash = {eb09719098969ac9704a2ed96546999b},
intrahash = {6c13206fbc5b5dc07fb61901e2805ed4},
keywords = {pattern relation semantic taxonomy},
location = {Jeju Island, Korea},
numpages = {11},
pages = {1135--1145},
publisher = {Association for Computational Linguistics},
series = {EMNLP-CoNLL '12},
timestamp = {2016-07-16T17:05:43.000+0200},
title = {PATTY: A Taxonomy of Relational Patterns with Semantic Types},
url = {http://dl.acm.org/citation.cfm?id=2390948.2391076},
year = 2012
}