Conference paper

ZHILA Alisa, YIH Wen-tau, MEEK Christopher, MIKOLOV Tomáš and ZWEIG Geoffrey. Combining Heterogeneous Models for Measuring Relational Similarity. In: Proceedings of NAACL-HLT 2013. Atlanata, Georgia: Association for Computational Linguistics, 2013, pp. 1000-1009. ISBN 978-1-937284-47-3. Available from:
Publication language:english
Original title:Combining Heterogeneous Models for Measuring Relational Similarity
Title (cs):Kombinace heterogenních modelů pro měření relační podobnosti
Proceedings:Proceedings of NAACL-HLT 2013
Conference:The 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Place:Atlanata, Georgia, US
Publisher:Association for Computational Linguistics
language modeling, heterogeneous models, recurrent neural networks
In this paper, we presented a system that combines heterogeneous models based on different information sources for measuring relational similarity.
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.
   author = {Alisa Zhila and Wen-tau Yih and Christopher Meek and
	Tom{\'{a}}{\v{s}} Mikolov and Geoffrey Zweig},
   title = {Combining Heterogeneous Models for Measuring Relational
   pages = {1000--1009},
   booktitle = {Proceedings of NAACL-HLT 2013},
   year = {2013},
   location = {Atlanata, Georgia, US},
   publisher = {Association for Computational Linguistics},
   ISBN = {978-1-937284-47-3},
   language = {english},
   url = {}

Your IPv4 address:
Switch to IPv6 connection

DNSSEC [dnssec]