A supervised classification approach for measuring relational similarity between word pairs

Danushka Bollegala, Yutaka Matsuo, Mitsuru Ishizuka

Research output: Contribution to journalArticle

Abstract

Measuring the relational similarity between word pairs is important in numerous natural language processing tasks such as solving word analogy questions, classifying noun-modifier relations and disambiguating word senses. We propose a supervised classification method to measure the similarity between semantic relations that exist between words in two word pairs. First, each pair of words is represented by a vector of automatically extracted lexical patterns. Then a binary Support Vector Machine is trained to recognize word pairs with similar semantic relations to a given word pair. To train and evaluate the proposed method, we use a benchmark dataset that contains 374 SAT multiple-choice word-analogy questions. To represent the relations that exist between two word pairs, we experiment with 11 different feature functions, including both symmetric and asymmetric feature functions. Our experimental results show that the proposed method outperforms several previously proposed relational similarity measures on this benchmark dataset, achieving an SAT score of 46.9.

Original languageEnglish
Pages (from-to)2227-2233
Number of pages7
JournalIEICE Transactions on Information and Systems
VolumeE94-D
Issue number11
DOIs
Publication statusPublished - 2011 Nov
Externally publishedYes

Fingerprint

Semantics
Support vector machines
Processing
Experiments

Keywords

  • Relational similarity
  • Supervised classification
  • Support vector machines
  • Word analogies

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

A supervised classification approach for measuring relational similarity between word pairs. / Bollegala, Danushka; Matsuo, Yutaka; Ishizuka, Mitsuru.

In: IEICE Transactions on Information and Systems, Vol. E94-D, No. 11, 11.2011, p. 2227-2233.

Research output: Contribution to journalArticle

Bollegala, Danushka ; Matsuo, Yutaka ; Ishizuka, Mitsuru. / A supervised classification approach for measuring relational similarity between word pairs. In: IEICE Transactions on Information and Systems. 2011 ; Vol. E94-D, No. 11. pp. 2227-2233.
@article{9c73fa08b4c14ec59b59276adfb3be59,
title = "A supervised classification approach for measuring relational similarity between word pairs",
abstract = "Measuring the relational similarity between word pairs is important in numerous natural language processing tasks such as solving word analogy questions, classifying noun-modifier relations and disambiguating word senses. We propose a supervised classification method to measure the similarity between semantic relations that exist between words in two word pairs. First, each pair of words is represented by a vector of automatically extracted lexical patterns. Then a binary Support Vector Machine is trained to recognize word pairs with similar semantic relations to a given word pair. To train and evaluate the proposed method, we use a benchmark dataset that contains 374 SAT multiple-choice word-analogy questions. To represent the relations that exist between two word pairs, we experiment with 11 different feature functions, including both symmetric and asymmetric feature functions. Our experimental results show that the proposed method outperforms several previously proposed relational similarity measures on this benchmark dataset, achieving an SAT score of 46.9.",
keywords = "Relational similarity, Supervised classification, Support vector machines, Word analogies",
author = "Danushka Bollegala and Yutaka Matsuo and Mitsuru Ishizuka",
year = "2011",
month = "11",
doi = "10.1587/transinf.E94.D.2227",
language = "English",
volume = "E94-D",
pages = "2227--2233",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "11",

}

TY - JOUR

T1 - A supervised classification approach for measuring relational similarity between word pairs

AU - Bollegala, Danushka

AU - Matsuo, Yutaka

AU - Ishizuka, Mitsuru

PY - 2011/11

Y1 - 2011/11

N2 - Measuring the relational similarity between word pairs is important in numerous natural language processing tasks such as solving word analogy questions, classifying noun-modifier relations and disambiguating word senses. We propose a supervised classification method to measure the similarity between semantic relations that exist between words in two word pairs. First, each pair of words is represented by a vector of automatically extracted lexical patterns. Then a binary Support Vector Machine is trained to recognize word pairs with similar semantic relations to a given word pair. To train and evaluate the proposed method, we use a benchmark dataset that contains 374 SAT multiple-choice word-analogy questions. To represent the relations that exist between two word pairs, we experiment with 11 different feature functions, including both symmetric and asymmetric feature functions. Our experimental results show that the proposed method outperforms several previously proposed relational similarity measures on this benchmark dataset, achieving an SAT score of 46.9.

AB - Measuring the relational similarity between word pairs is important in numerous natural language processing tasks such as solving word analogy questions, classifying noun-modifier relations and disambiguating word senses. We propose a supervised classification method to measure the similarity between semantic relations that exist between words in two word pairs. First, each pair of words is represented by a vector of automatically extracted lexical patterns. Then a binary Support Vector Machine is trained to recognize word pairs with similar semantic relations to a given word pair. To train and evaluate the proposed method, we use a benchmark dataset that contains 374 SAT multiple-choice word-analogy questions. To represent the relations that exist between two word pairs, we experiment with 11 different feature functions, including both symmetric and asymmetric feature functions. Our experimental results show that the proposed method outperforms several previously proposed relational similarity measures on this benchmark dataset, achieving an SAT score of 46.9.

KW - Relational similarity

KW - Supervised classification

KW - Support vector machines

KW - Word analogies

UR - http://www.scopus.com/inward/record.url?scp=80155170175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80155170175&partnerID=8YFLogxK

U2 - 10.1587/transinf.E94.D.2227

DO - 10.1587/transinf.E94.D.2227

M3 - Article

VL - E94-D

SP - 2227

EP - 2233

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 11

ER -