论文信息 - Remixing Headlines for Context-Appropriate Flavor Text

Remixing Headlines for Context-Appropriate Flavor Text

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 hand-coded language models from the user.

Judith van Stegeren | Mariët Theune

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

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

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

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

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

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

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

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