UTD: Determining Relational Similarity Using Lexical Patterns
B. Rink, and S. Harabagiu. Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the Main Conference and the Shared Task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation, page 413--418. Stroudsburg, PA, USA, Association for Computational Linguistics, (2012)
Abstract
In this paper we present our approach for assigning degrees of relational similarity to pairs of words in the SemEval-2012 Task 2. To measure relational similarity we employed lexical patterns that can match against word pairs within a large corpus of 12 million documents. Patterns are weighted by obtaining statistically estimated lower bounds on their precision for extracting word pairs from a given relation. Finally, word pairs are ranked based on a model predicting the probability that they belong to the relation of interest. This approach achieved the best results on the SemEval 2012 Task 2, obtaining a Spearman correlation of 0.229 and an accuracy on reproducing human answers to MaxDiff questions of 39.4%.
Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the Main Conference and the Shared Task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
%0 Conference Paper
%1 rink2012determining
%A Rink, Bryan
%A Harabagiu, Sanda
%B Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the Main Conference and the Shared Task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
%C Stroudsburg, PA, USA
%D 2012
%I Association for Computational Linguistics
%K relational semeval2012 similarity utd
%P 413--418
%T UTD: Determining Relational Similarity Using Lexical Patterns
%U http://dl.acm.org/citation.cfm?id=2387636.2387702
%X In this paper we present our approach for assigning degrees of relational similarity to pairs of words in the SemEval-2012 Task 2. To measure relational similarity we employed lexical patterns that can match against word pairs within a large corpus of 12 million documents. Patterns are weighted by obtaining statistically estimated lower bounds on their precision for extracting word pairs from a given relation. Finally, word pairs are ranked based on a model predicting the probability that they belong to the relation of interest. This approach achieved the best results on the SemEval 2012 Task 2, obtaining a Spearman correlation of 0.229 and an accuracy on reproducing human answers to MaxDiff questions of 39.4%.
@inproceedings{rink2012determining,
abstract = {In this paper we present our approach for assigning degrees of relational similarity to pairs of words in the SemEval-2012 Task 2. To measure relational similarity we employed lexical patterns that can match against word pairs within a large corpus of 12 million documents. Patterns are weighted by obtaining statistically estimated lower bounds on their precision for extracting word pairs from a given relation. Finally, word pairs are ranked based on a model predicting the probability that they belong to the relation of interest. This approach achieved the best results on the SemEval 2012 Task 2, obtaining a Spearman correlation of 0.229 and an accuracy on reproducing human answers to MaxDiff questions of 39.4%.},
acmid = {2387702},
added-at = {2016-06-30T15:07:08.000+0200},
address = {Stroudsburg, PA, USA},
author = {Rink, Bryan and Harabagiu, Sanda},
biburl = {https://www.bibsonomy.org/bibtex/2f45a3fd9b34d25b0bebb80ba6824ca1e/thoni},
booktitle = {Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the Main Conference and the Shared Task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation},
interhash = {de03faa3f5e6d942dc5ae78d0650b306},
intrahash = {f45a3fd9b34d25b0bebb80ba6824ca1e},
keywords = {relational semeval2012 similarity utd},
location = {Montr\éal, Canada},
numpages = {6},
pages = {413--418},
publisher = {Association for Computational Linguistics},
series = {SemEval '12},
timestamp = {2016-09-06T08:23:07.000+0200},
title = {UTD: Determining Relational Similarity Using Lexical Patterns},
url = {http://dl.acm.org/citation.cfm?id=2387636.2387702},
year = 2012
}