Publication Details

Combining Heterogeneous Models for Measuring Relational Similarity

ZHILA, A.; YIH, W.; MEEK, C.; MIKOLOV, T.; ZWEIG, G. Combining Heterogeneous Models for Measuring Relational Similarity. Proceedings of NAACL-HLT 2013. Atlanata, Georgia: Association for Computational Linguistics, 2013. p. 1000-1009. ISBN: 978-1-937284-47-3.
Czech title
Kombinace heterogenních modelů pro měření relační podobnosti
Type
conference paper
Language
English
Authors
Zhila Alisa (FIT)
Yih Wen-tau (FIT)
Meek Christopher (FIT)
Mikolov Tomáš, Ing., Ph.D.
Zweig Geoffrey
URL
Keywords

language modeling, heterogeneous models, recurrent neural networks

Abstract

In this paper, we presented a system that combines heterogeneous models based on different information sources for measuring relational similarity.

Annotation

In this work, we study the problem of measuring relational similarity between two word pairs (e.g., silverware:fork and clothing:shirt). Due to the large number of possible relations, we argue that it is important to combine multiple models based on heterogeneous information sources. Our overall system consists of two novel general-purpose relational similarity models and three specific word relation models. When evaluated in the setting of a recently proposed SemEval-2012 task, our approach outperforms the previous best system substantially, achieving a 54.1% relative increase in Spearmans rank correlation.

Published
2013
Pages
1000–1009
Proceedings
Proceedings of NAACL-HLT 2013
ISBN
978-1-937284-47-3
Publisher
Association for Computational Linguistics
Place
Atlanata, Georgia
BibTeX
@inproceedings{BUT105978,
  author="Alisa {Zhila} and Wen-tau {Yih} and Christopher {Meek} and Tomáš {Mikolov} and Geoffrey {Zweig}",
  title="Combining Heterogeneous Models for Measuring Relational Similarity",
  booktitle="Proceedings of NAACL-HLT 2013",
  year="2013",
  pages="1000--1009",
  publisher="Association for Computational Linguistics",
  address="Atlanata, Georgia",
  isbn="978-1-937284-47-3",
  url="http://www.aclweb.org/anthology/N/N13/N13-1120.pdf"
}
Back to top