Oxymoron generation using an association word corpus and a large-scale N-gram corpus

Hiroaki Yamane, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

Oxymorons are combinations of contradictory or incongruous words and are typically used to draw readers’ attention to a text. This paper proposes a method to generate oxymorons using an association word corpus and a large-scale N-gram corpus. First, adjectives are fed as input into the proposed system. Then, antonym pairs are extracted from the N-gram corpus. Using the antonym pairs and the association word corpus, candidates are generated. Candidates are finalized or eliminated according to their suitability and attractiveness. To determine suitability, pointwise mutual information (PMI) is employed to exclude grammatically unnatural expressions. To determine attractiveness, PMI, gap of frequency of the oxymoron candidates, and WordNet are used. The generated combinations of oxymorons indicate the potential effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)919-927
Number of pages9
JournalSoft Computing
Volume19
Issue number4
DOIs
Publication statusPublished - 2015

Fingerprint

N-gram
Mutual Information
WordNet
Corpus

Keywords

  • Association word
  • N-gram
  • Oxymoron
  • Sensibility
  • Sentence generation

ASJC Scopus subject areas

  • Software
  • Geometry and Topology
  • Theoretical Computer Science

Cite this

Oxymoron generation using an association word corpus and a large-scale N-gram corpus. / Yamane, Hiroaki; Hagiwara, Masafumi.

In: Soft Computing, Vol. 19, No. 4, 2015, p. 919-927.

Research output: Contribution to journalArticle

@article{5c4577187ff2454e9df20ef36d6f1563,
title = "Oxymoron generation using an association word corpus and a large-scale N-gram corpus",
abstract = "Oxymorons are combinations of contradictory or incongruous words and are typically used to draw readers’ attention to a text. This paper proposes a method to generate oxymorons using an association word corpus and a large-scale N-gram corpus. First, adjectives are fed as input into the proposed system. Then, antonym pairs are extracted from the N-gram corpus. Using the antonym pairs and the association word corpus, candidates are generated. Candidates are finalized or eliminated according to their suitability and attractiveness. To determine suitability, pointwise mutual information (PMI) is employed to exclude grammatically unnatural expressions. To determine attractiveness, PMI, gap of frequency of the oxymoron candidates, and WordNet are used. The generated combinations of oxymorons indicate the potential effectiveness of the proposed method.",
keywords = "Association word, N-gram, Oxymoron, Sensibility, Sentence generation",
author = "Hiroaki Yamane and Masafumi Hagiwara",
year = "2015",
doi = "10.1007/s00500-014-1430-6",
language = "English",
volume = "19",
pages = "919--927",
journal = "Soft Computing",
issn = "1432-7643",
publisher = "Springer Verlag",
number = "4",

}

TY - JOUR

T1 - Oxymoron generation using an association word corpus and a large-scale N-gram corpus

AU - Yamane, Hiroaki

AU - Hagiwara, Masafumi

PY - 2015

Y1 - 2015

N2 - Oxymorons are combinations of contradictory or incongruous words and are typically used to draw readers’ attention to a text. This paper proposes a method to generate oxymorons using an association word corpus and a large-scale N-gram corpus. First, adjectives are fed as input into the proposed system. Then, antonym pairs are extracted from the N-gram corpus. Using the antonym pairs and the association word corpus, candidates are generated. Candidates are finalized or eliminated according to their suitability and attractiveness. To determine suitability, pointwise mutual information (PMI) is employed to exclude grammatically unnatural expressions. To determine attractiveness, PMI, gap of frequency of the oxymoron candidates, and WordNet are used. The generated combinations of oxymorons indicate the potential effectiveness of the proposed method.

AB - Oxymorons are combinations of contradictory or incongruous words and are typically used to draw readers’ attention to a text. This paper proposes a method to generate oxymorons using an association word corpus and a large-scale N-gram corpus. First, adjectives are fed as input into the proposed system. Then, antonym pairs are extracted from the N-gram corpus. Using the antonym pairs and the association word corpus, candidates are generated. Candidates are finalized or eliminated according to their suitability and attractiveness. To determine suitability, pointwise mutual information (PMI) is employed to exclude grammatically unnatural expressions. To determine attractiveness, PMI, gap of frequency of the oxymoron candidates, and WordNet are used. The generated combinations of oxymorons indicate the potential effectiveness of the proposed method.

KW - Association word

KW - N-gram

KW - Oxymoron

KW - Sensibility

KW - Sentence generation

UR - http://www.scopus.com/inward/record.url?scp=84924957532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924957532&partnerID=8YFLogxK

U2 - 10.1007/s00500-014-1430-6

DO - 10.1007/s00500-014-1430-6

M3 - Article

AN - SCOPUS:84924957532

VL - 19

SP - 919

EP - 927

JO - Soft Computing

JF - Soft Computing

SN - 1432-7643

IS - 4

ER -