Remixing Headlines for Context-Appropriate Flavor Text

Judith van Stegeren; Mariët Theune

doi:10.1109/CIG.2019.8848050

Remixing Headlines for Context-Appropriate Flavor Text

Judith van Stegeren
, Mariët Theune

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

1 Citation (Scopus)

114 Downloads (Pure)

Abstract

We describe a prototype of Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as flavor text in games. Churnalist creates new headlines by remixing existing headlines. It extracts seed words from free text input, searches for related words in a dataset of word embeddings and uses these words in the new headlines. The system requires no linguistic expertise or handcoded language models from the user.

Original language	English
Title of host publication	Proceedings of the IEEE Conference On Games (COG) 2019
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	2
ISBN (Electronic)	9781728118840
ISBN (Print)	978-1-7281-1885-7
DOIs	https://doi.org/10.1109/CIG.2019.8848050
Publication status	Published - 20 Aug 2019
Event	IEEE Conference On Games 2019 - Queen Mary University of London, London, United Kingdom Duration: 20 Aug 2019 → 23 Aug 2019 http://ieee-cog.org/

Conference

Conference	IEEE Conference On Games 2019
Abbreviated title	IEEE COG 2019
Country/Territory	United Kingdom
City	London
Period	20/08/19 → 23/08/19
Internet address	http://ieee-cog.org/

Keywords

Flavor text
Headline generation
Context
Text generation
Remixing
Games

Access to Document

10.1109/CIG.2019.8848050

IEEE Conference On Games 2019
van Stegeren, J. E. (Participant) & Mavromoustakos Blom, P. (Participant)
20 Aug 2019 → 23 Aug 2019
Activity: Participating in or organising an event › Participating in a conference, workshop, ...

Cite this

@inproceedings{bcf2838875da41e59f17c6fa85758aac,

title = "Remixing Headlines for Context-Appropriate Flavor Text",

abstract = "We describe a prototype of Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as flavor text in games. Churnalist creates new headlines by remixing existing headlines. It extracts seed words from free text input, searches for related words in a dataset of word embeddings and uses these words in the new headlines. The system requires no linguistic expertise or handcoded language models from the user.",

keywords = "Flavor text, Headline generation, Context, Text generation, Remixing, Games",

author = "\{van Stegeren\}, Judith and Mari{\"e}t Theune",

year = "2019",

month = aug,

day = "20",

doi = "10.1109/CIG.2019.8848050",

language = "English",

isbn = "978-1-7281-1885-7",

booktitle = "Proceedings of the IEEE Conference On Games (COG) 2019",

publisher = "IEEE",

address = "United States",

note = "IEEE Conference On Games 2019, IEEE COG 2019 ; Conference date: 20-08-2019 Through 23-08-2019",

url = "http://ieee-cog.org/",

}

TY - GEN

T1 - Remixing Headlines for Context-Appropriate Flavor Text

AU - van Stegeren, Judith

AU - Theune, Mariët

PY - 2019/8/20

Y1 - 2019/8/20

N2 - We describe a prototype of Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as flavor text in games. Churnalist creates new headlines by remixing existing headlines. It extracts seed words from free text input, searches for related words in a dataset of word embeddings and uses these words in the new headlines. The system requires no linguistic expertise or handcoded language models from the user.

AB - We describe a prototype of Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as flavor text in games. Churnalist creates new headlines by remixing existing headlines. It extracts seed words from free text input, searches for related words in a dataset of word embeddings and uses these words in the new headlines. The system requires no linguistic expertise or handcoded language models from the user.

KW - Flavor text

KW - Headline generation

KW - Context

KW - Text generation

KW - Remixing

KW - Games

U2 - 10.1109/CIG.2019.8848050

DO - 10.1109/CIG.2019.8848050

M3 - Conference contribution

SN - 978-1-7281-1885-7

BT - Proceedings of the IEEE Conference On Games (COG) 2019

PB - IEEE

CY - Piscataway, NJ

T2 - IEEE Conference On Games 2019

Y2 - 20 August 2019 through 23 August 2019

ER -

Remixing Headlines for Context-Appropriate Flavor Text

Abstract

Conference

Keywords

Access to Document

Fingerprint

Activities

IEEE Conference On Games 2019

Cite this