Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text

Judith van Stegeren; Mariet  Theune

Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text

Judith van Stegeren, Mariet Theune

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

231 Downloads (Pure)

Abstract

We present Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as ‘flavor text’ in games. Churnalist creates new headlines from existing headlines with text modification. It extracts seed words from free text input, queries a knowledge base for related words and uses these words in the new headlines. Churnalist’s knowledge base consists of a dataset of pre-trained word embeddings, thus requiring no linguistic expertise or hand-coded models from the user.

Original language	English
Title of host publication	Proceedings of the 10th International Conference on Computational Creativity
Editors	Kazjon Grace, Michael Cook, Dan Ventura, Mary Lou Maher
Publisher	Association for Computational Creativity
Pages	65-72
Number of pages	8
ISBN (Electronic)	978-989-54160-1-1
Publication status	Published - Jun 2019
Event	10th International Conference on Computational Creativity - UNC Charlotte, Charlotte, United States Duration: 17 Jun 2019 → 21 Jun 2019 http://computationalcreativity.net/iccc2019/

Conference

Conference	10th International Conference on Computational Creativity
Abbreviated title	ICCC 2019
Country/Territory	United States
City	Charlotte
Period	17/06/19 → 21/06/19
Internet address	http://computationalcreativity.net/iccc2019/

Keywords

Natural language generation
Text modification
Headline generation
Procedural content generation
Text generation
Video games
flavor text
Computational creativity

Access to Document

vanstegeren2019churnalistFinal published version, 198 KB

10th International Conference on Computational Creativity
van Stegeren, J. (Participant)
17 Jun 2019 → 21 Jun 2019
Activity: Participating in or organising an event › Participating in a conference, workshop, ...

Cite this

@inproceedings{c1b65b2f6cfb4886a17283483f6bec04,

title = "Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text",

abstract = "We present Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as {\textquoteleft}flavor text{\textquoteright} in games. Churnalist creates new headlines from existing headlines with text modification. It extracts seed words from free text input, queries a knowledge base for related words and uses these words in the new headlines. Churnalist{\textquoteright}s knowledge base consists of a dataset of pre-trained word embeddings, thus requiring no linguistic expertise or hand-coded models from the user.",

keywords = "Natural language generation, Text modification, Headline generation, Procedural content generation, Text generation, Video games, flavor text, Computational creativity",

author = "{van Stegeren}, Judith and Mariet Theune",

year = "2019",

month = jun,

language = "English",

pages = "65--72",

editor = "Kazjon Grace and Michael Cook and Dan Ventura and Maher, {Mary Lou}",

booktitle = "Proceedings of the 10th International Conference on Computational Creativity",

publisher = "Association for Computational Creativity",

note = "10th International Conference on Computational Creativity, ICCC 2019 ; Conference date: 17-06-2019 Through 21-06-2019",

url = "http://computationalcreativity.net/iccc2019/",

}

van Stegeren, J & Theune, M 2019, Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text. in K Grace, M Cook, D Ventura & ML Maher (eds), Proceedings of the 10th International Conference on Computational Creativity. Association for Computational Creativity, pp. 65-72, 10th International Conference on Computational Creativity, Charlotte, North Carolina, United States, 17/06/19.

Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text. / van Stegeren, Judith; Theune, Mariet .
Proceedings of the 10th International Conference on Computational Creativity. ed. / Kazjon Grace; Michael Cook; Dan Ventura; Mary Lou Maher. Association for Computational Creativity, 2019. p. 65-72.

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

TY - GEN

T1 - Churnalist

T2 - 10th International Conference on Computational Creativity

AU - van Stegeren, Judith

AU - Theune, Mariet

PY - 2019/6

Y1 - 2019/6

N2 - We present Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as ‘flavor text’ in games. Churnalist creates new headlines from existing headlines with text modification. It extracts seed words from free text input, queries a knowledge base for related words and uses these words in the new headlines. Churnalist’s knowledge base consists of a dataset of pre-trained word embeddings, thus requiring no linguistic expertise or hand-coded models from the user.

AB - We present Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as ‘flavor text’ in games. Churnalist creates new headlines from existing headlines with text modification. It extracts seed words from free text input, queries a knowledge base for related words and uses these words in the new headlines. Churnalist’s knowledge base consists of a dataset of pre-trained word embeddings, thus requiring no linguistic expertise or hand-coded models from the user.

KW - Natural language generation

KW - Text modification

KW - Headline generation

KW - Procedural content generation

KW - Text generation

KW - Video games

KW - flavor text

KW - Computational creativity

M3 - Conference contribution

SP - 65

EP - 72

BT - Proceedings of the 10th International Conference on Computational Creativity

A2 - Grace, Kazjon

A2 - Cook, Michael

A2 - Ventura, Dan

A2 - Maher, Mary Lou

PB - Association for Computational Creativity

Y2 - 17 June 2019 through 21 June 2019

ER -

Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text

Abstract

Conference

Keywords

Access to Document

Fingerprint

Activities

10th International Conference on Computational Creativity

Cite this