Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Many linguistic creativity applications rely heavily on knowledge of nouns and their properties.
However, such knowledge sources are scarce and limited.
We present a graph-based approach for expanding and weighting properties of nouns with given initial, non-weighted properties.
In this paper, we focus on famous characters, either real or fictional, and categories of people, such as Actor, Hero, Child etc.
In our case study, we started with an average of 11 and 25 initial properties for characters and categories, for which the method found 63 and 132 additional properties, respectively.
An empirical evaluation shows that the expanded properties and weights are consistent with human judgement. The resulting knowledge base can be utilized in creation of figurative language. For instance, metaphors based on famous characters can be used in various applications including story generation, creative writing, advertising and comic generation.
Original languageEnglish
Title of host publicationProceedings of the 8th International Conference on Computational Creativity (ICCC'17)
EditorsAshok Goel, Anna Jordanous, Alison Pease
Number of pages8
Place of PublicationAtlanta, GA
PublisherGeorgia Institute of Technology
Publication date23 Jun 2017
Pages25-32
ISBN (Electronic)978-0-692-89564-1
Publication statusPublished - 23 Jun 2017
MoE publication typeA4 Article in conference proceedings
EventInternational Conference on Computational Creativity - Atlanta, United States
Duration: 19 Jun 201723 Jun 2017
Conference number: 8

Fields of Science

  • 113 Computer and information sciences
  • Artificial Intelligence
  • Computational Creativity

Cite this

Alnajjar, K., Hämäläinen, M., Chen, H., & Toivonen, H. (2017). Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity. In A. Goel, A. Jordanous, & A. Pease (Eds.), Proceedings of the 8th International Conference on Computational Creativity (ICCC'17) (pp. 25-32). Atlanta, GA: Georgia Institute of Technology .
Alnajjar, Khalid ; Hämäläinen, Mika ; Chen, Hanyang ; Toivonen, Hannu. / Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity. Proceedings of the 8th International Conference on Computational Creativity (ICCC'17). editor / Ashok Goel ; Anna Jordanous ; Alison Pease. Atlanta, GA : Georgia Institute of Technology , 2017. pp. 25-32
@inproceedings{dd5df0d0adb94879944bf03d9cd466ae,
title = "Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity",
abstract = "Many linguistic creativity applications rely heavily on knowledge of nouns and their properties. However, such knowledge sources are scarce and limited.We present a graph-based approach for expanding and weighting properties of nouns with given initial, non-weighted properties. In this paper, we focus on famous characters, either real or fictional, and categories of people, such as Actor, Hero, Child etc. In our case study, we started with an average of 11 and 25 initial properties for characters and categories, for which the method found 63 and 132 additional properties, respectively.An empirical evaluation shows that the expanded properties and weights are consistent with human judgement. The resulting knowledge base can be utilized in creation of figurative language. For instance, metaphors based on famous characters can be used in various applications including story generation, creative writing, advertising and comic generation.",
keywords = "113 Computer and information sciences, Artificial Intelligence, Computational Creativity",
author = "Khalid Alnajjar and Mika H{\"a}m{\"a}l{\"a}inen and Hanyang Chen and Hannu Toivonen",
note = "Volume: Proceeding volume:",
year = "2017",
month = "6",
day = "23",
language = "English",
pages = "25--32",
editor = "Ashok Goel and Anna Jordanous and Alison Pease",
booktitle = "Proceedings of the 8th International Conference on Computational Creativity (ICCC'17)",
publisher = "Georgia Institute of Technology",
address = "Georgia",

}

Alnajjar, K, Hämäläinen, M, Chen, H & Toivonen, H 2017, Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity. in A Goel, A Jordanous & A Pease (eds), Proceedings of the 8th International Conference on Computational Creativity (ICCC'17). Georgia Institute of Technology , Atlanta, GA, pp. 25-32, International Conference on Computational Creativity, Atlanta, United States, 19/06/2017.

Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity. / Alnajjar, Khalid; Hämäläinen, Mika; Chen, Hanyang; Toivonen, Hannu.

Proceedings of the 8th International Conference on Computational Creativity (ICCC'17). ed. / Ashok Goel; Anna Jordanous; Alison Pease. Atlanta, GA : Georgia Institute of Technology , 2017. p. 25-32.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

TY - GEN

T1 - Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity

AU - Alnajjar, Khalid

AU - Hämäläinen, Mika

AU - Chen, Hanyang

AU - Toivonen, Hannu

N1 - Volume: Proceeding volume:

PY - 2017/6/23

Y1 - 2017/6/23

N2 - Many linguistic creativity applications rely heavily on knowledge of nouns and their properties. However, such knowledge sources are scarce and limited.We present a graph-based approach for expanding and weighting properties of nouns with given initial, non-weighted properties. In this paper, we focus on famous characters, either real or fictional, and categories of people, such as Actor, Hero, Child etc. In our case study, we started with an average of 11 and 25 initial properties for characters and categories, for which the method found 63 and 132 additional properties, respectively.An empirical evaluation shows that the expanded properties and weights are consistent with human judgement. The resulting knowledge base can be utilized in creation of figurative language. For instance, metaphors based on famous characters can be used in various applications including story generation, creative writing, advertising and comic generation.

AB - Many linguistic creativity applications rely heavily on knowledge of nouns and their properties. However, such knowledge sources are scarce and limited.We present a graph-based approach for expanding and weighting properties of nouns with given initial, non-weighted properties. In this paper, we focus on famous characters, either real or fictional, and categories of people, such as Actor, Hero, Child etc. In our case study, we started with an average of 11 and 25 initial properties for characters and categories, for which the method found 63 and 132 additional properties, respectively.An empirical evaluation shows that the expanded properties and weights are consistent with human judgement. The resulting knowledge base can be utilized in creation of figurative language. For instance, metaphors based on famous characters can be used in various applications including story generation, creative writing, advertising and comic generation.

KW - 113 Computer and information sciences

KW - Artificial Intelligence

KW - Computational Creativity

M3 - Conference contribution

SP - 25

EP - 32

BT - Proceedings of the 8th International Conference on Computational Creativity (ICCC'17)

A2 - Goel, Ashok

A2 - Jordanous, Anna

A2 - Pease, Alison

PB - Georgia Institute of Technology

CY - Atlanta, GA

ER -

Alnajjar K, Hämäläinen M, Chen H, Toivonen H. Expanding and Weighting Stereotypical Properties of Human Characters for Linguistic Creativity. In Goel A, Jordanous A, Pease A, editors, Proceedings of the 8th International Conference on Computational Creativity (ICCC'17). Atlanta, GA: Georgia Institute of Technology . 2017. p. 25-32