Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text

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.

[1]  Benjamin Van Durme,et al.  Annotated Gigaword , 2012, AKBC-WEKEX@NAACL-HLT.

[2]  Ashwin Ram,et al.  Emotionally Driven Natural Language Generation for Personality Rich Characters in Interactive Games , 2007, AIIDE.

[3]  Jason Grinblat,et al.  Subverting historical cause & effect: generation of mythic biographies in Caves of Qud , 2017, FDG.

[4]  Simon Colton,et al.  On the Notion of Framing in Computational Creativity , 2012, ICCC.

[5]  Michele Banko,et al.  Headline Generation Based on Statistical Translation , 2000, ACL.

[6]  Julian Togelius,et al.  Experience-Driven Procedural Content Generation , 2011, IEEE Transactions on Affective Computing.

[7]  Gözde Özbal,et al.  BRAINSUP: Brainstorming Support for Creative Sentence Generation , 2013, ACL.

[8]  Dan Ventura,et al.  Text Transformation Via Constraints and Word Embedding , 2017, ICCC.

[9]  Erik D. Demaine,et al.  Cookie Clicker , 2020, Graphs Comb..

[10]  Richard M. Schwartz,et al.  Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation , 2003, HLT-NAACL 2003.

[11]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[12]  Marilyn A. Walker,et al.  Automating Direct Speech Variations in Stories and Games , 2017, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[13]  Ralf Klabunde,et al.  Greetings Generation in Video Role Playing Games , 2013, ENLG.

[14]  Martin Znidarsic,et al.  BISLON: BISociative SLOgaN generation based on stylistic literary devices , 2018, ICCC.

[15]  Hugo Gonçalo Oliveira.  O Poeta Artificial 2.0: Increasing Meaningfulness in a Poetry Generation Twitter bot , 2017, CC-NLG@INLG.

[16]  Gözde Özbal,et al.  Slogans Are Not Forever: Adapting Linguistic Expressions to the News , 2015, IJCAI.

[17]  Hongyan Jing,et al.  Sentence Reduction for Automatic Text Summarization , 2000, ANLP.

[18]  Tony Veale,et al.  3. The shape of tweets to come: Automating language play in social networks , 2016 .

[19]  Gözde Özbal,et al.  Heady-Lines: A Creative Generator Of Newspaper Headlines , 2016, IUI Companion.

[20]  Hugo Gonçalo Oliveira.  PoeTryMe : a versatile platform for poetry generation , 2012 .

[21]  Fabrizio Silvestri,et al.  HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space , 2015, NAACL.

[22]  Marina Daecher.  Fluid Concepts And Creative Analogies Computer Models Of The Fundamental Mechanisms Of Thought , 2016 .

[23]  Zhiyuan Liu,et al.  Recent Advances on Neural Headline Generation , 2017, Journal of Computer Science and Technology.

[24]  Simon Hegelich,et al.  Are Social Bots on Twitter Political Actors? Empirical Evidence from a Ukrainian Social Botnet , 2016, ICWSM.