Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification

Dan Assaf; Yair Neuman; Yohai Cohen; Shlomo Argamon; Newton Howard; Mark Last; Ophir Frieder; Moshe Koppel

doi:10.1109/CCMB.2013.6609166

Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification

Dan Assaf, Yair Neuman, Yohai Cohen, Shlomo Argamon, Newton Howard, Mark Last, Ophir Frieder, Moshe Koppel

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

19 Scopus citations

Abstract

Distinguishing between literal and metaphorical language is a major challenge facing natural language processing. Heuristically, metaphors can be divided into three general types in which type III metaphors are those involving an adjective-noun relationship (e.g. 'dark humor'). This paper describes our approach for automatic identification of type III metaphors. We propose a new algorithm, the Concrete-Category Overlap (CCO) algorithm, that distinguishes between literal and metaphorical use of adjective-noun relationships and evaluate it on two data sets of adjective-noun phrases. Our results point to the superiority of the CCO algorithm to past and contemporary approaches in determining the presence and conceptual significance of metaphors, and provide a better understanding of the conditions under which each algorithm should be applied.

Original language	English
Title of host publication	Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Publisher	Institute of Electrical and Electronics Engineers
Pages	60-65
Number of pages	6
ISBN (Print)	9781467358712
DOIs	https://doi.org/10.1109/CCMB.2013.6609166
State	Published - 1 Jan 2013
Event	2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore Duration: 16 Apr 2013 → 19 Apr 2013

Publication series

Name	Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

Conference

Conference	2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Country/Territory	Singapore
City	Singapore
Period	16/04/13 → 19/04/13

Keywords

computational intelligence
computational linguistics
metaphor
natural language processing

ASJC Scopus subject areas

Artificial Intelligence
Modeling and Simulation

Access to Document

10.1109/CCMB.2013.6609166

Cite this

Assaf, D., Neuman, Y., Cohen, Y., Argamon, S., Howard, N., Last, M., Frieder, O., & Koppel, M. (2013). Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 60-65). [6609166] (Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CCMB.2013.6609166

Assaf, Dan ; Neuman, Yair ; Cohen, Yohai et al. / Why 'dark thoughts' aren't really dark : A novel algorithm for metaphor identification. Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. Institute of Electrical and Electronics Engineers, 2013. pp. 60-65 (Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013).

@inproceedings{a9b8a6e2c0e246db92c02aa55708616a,

title = "Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification",

abstract = "Distinguishing between literal and metaphorical language is a major challenge facing natural language processing. Heuristically, metaphors can be divided into three general types in which type III metaphors are those involving an adjective-noun relationship (e.g. 'dark humor'). This paper describes our approach for automatic identification of type III metaphors. We propose a new algorithm, the Concrete-Category Overlap (CCO) algorithm, that distinguishes between literal and metaphorical use of adjective-noun relationships and evaluate it on two data sets of adjective-noun phrases. Our results point to the superiority of the CCO algorithm to past and contemporary approaches in determining the presence and conceptual significance of metaphors, and provide a better understanding of the conditions under which each algorithm should be applied.",

keywords = "computational intelligence, computational linguistics, metaphor, natural language processing",

author = "Dan Assaf and Yair Neuman and Yohai Cohen and Shlomo Argamon and Newton Howard and Mark Last and Ophir Frieder and Moshe Koppel",

year = "2013",

month = jan,

day = "1",

doi = "10.1109/CCMB.2013.6609166",

language = "English",

isbn = "9781467358712",

series = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "60--65",

booktitle = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

address = "United States",

note = "2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 ; Conference date: 16-04-2013 Through 19-04-2013",

}

Assaf, D, Neuman, Y, Cohen, Y, Argamon, S, Howard, N, Last, M, Frieder, O & Koppel, M 2013, Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification. in Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6609166, Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Institute of Electrical and Electronics Engineers, pp. 60-65, 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, Singapore, 16/04/13. https://doi.org/10.1109/CCMB.2013.6609166

Why 'dark thoughts' aren't really dark : A novel algorithm for metaphor identification. / Assaf, Dan; Neuman, Yair; Cohen, Yohai et al.

Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. Institute of Electrical and Electronics Engineers, 2013. p. 60-65 6609166 (Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Why 'dark thoughts' aren't really dark

T2 - 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

AU - Assaf, Dan

AU - Neuman, Yair

AU - Cohen, Yohai

AU - Argamon, Shlomo

AU - Howard, Newton

AU - Last, Mark

AU - Frieder, Ophir

AU - Koppel, Moshe

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Distinguishing between literal and metaphorical language is a major challenge facing natural language processing. Heuristically, metaphors can be divided into three general types in which type III metaphors are those involving an adjective-noun relationship (e.g. 'dark humor'). This paper describes our approach for automatic identification of type III metaphors. We propose a new algorithm, the Concrete-Category Overlap (CCO) algorithm, that distinguishes between literal and metaphorical use of adjective-noun relationships and evaluate it on two data sets of adjective-noun phrases. Our results point to the superiority of the CCO algorithm to past and contemporary approaches in determining the presence and conceptual significance of metaphors, and provide a better understanding of the conditions under which each algorithm should be applied.

AB - Distinguishing between literal and metaphorical language is a major challenge facing natural language processing. Heuristically, metaphors can be divided into three general types in which type III metaphors are those involving an adjective-noun relationship (e.g. 'dark humor'). This paper describes our approach for automatic identification of type III metaphors. We propose a new algorithm, the Concrete-Category Overlap (CCO) algorithm, that distinguishes between literal and metaphorical use of adjective-noun relationships and evaluate it on two data sets of adjective-noun phrases. Our results point to the superiority of the CCO algorithm to past and contemporary approaches in determining the presence and conceptual significance of metaphors, and provide a better understanding of the conditions under which each algorithm should be applied.

KW - computational intelligence

KW - computational linguistics

KW - metaphor

KW - natural language processing

UR - http://www.scopus.com/inward/record.url?scp=84886494875&partnerID=8YFLogxK

U2 - 10.1109/CCMB.2013.6609166

DO - 10.1109/CCMB.2013.6609166

M3 - Conference contribution

AN - SCOPUS:84886494875

SN - 9781467358712

T3 - Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

SP - 60

EP - 65

BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

PB - Institute of Electrical and Electronics Engineers

Y2 - 16 April 2013 through 19 April 2013

ER -

Assaf D, Neuman Y, Cohen Y, Argamon S, Howard N, Last M et al. Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. Institute of Electrical and Electronics Engineers. 2013. p. 60-65. 6609166. (Proceedings of the 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). doi: 10.1109/CCMB.2013.6609166

Why 'dark thoughts' aren't really dark: A novel algorithm for metaphor identification

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this