Show simple item record

dc.contributor.authorCHOURDAKIS, ETen_US
dc.contributor.authorREISS, JDen_US
dc.contributor.authorWorkshop on Computational Creativity in Natural Language Generationen_US
dc.date.accessioned2017-10-05T10:51:26Z
dc.date.available2017-07-03en_US
dc.date.issued2017-09-04en_US
dc.date.submitted2017-09-08T21:17:19.433Z
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/26824
dc.description.abstractThis paper proposes a method for learning how to generate narrative by recombining sentences from a previous collection. Given a corpus of story events categorised into 9 topics, we approximate a deep reinforcement learning agent policy to recombine them in order to satisfy narrative structure. We also propose an evaluation of such a system. The evaluation is based on coherence, interest, and topic, in order to figure how much sense the generated stories make, how interesting they are, and examine whether new narrative topics can emerge.en_US
dc.subjectstory generationen_US
dc.titleConstructing narrative using a generative model and continuous action policiesen_US
dc.typeConference Proceeding
dc.rights.holder© The Author(s) 2017
pubs.notesNot knownen_US
pubs.notesNote this is work in progressen_US
pubs.organisational-group/Queen Mary University of London
pubs.organisational-group/Queen Mary University of London/Faculty of Science & Engineering
pubs.organisational-group/Queen Mary University of London/Faculty of Science & Engineering/Electronic Engineering and Computer Science - Electronic Engineering - Research Students
pubs.organisational-group/Queen Mary University of London/Faculty of Science & Engineering/Electronic Engineering and Computer Science - Staff
pubs.organisational-group/Queen Mary University of London/Faculty Reporting - Research Students
pubs.organisational-group/Queen Mary University of London/Faculty Reporting - Research Students/Faculty of Science & Engineering PGRs
pubs.organisational-group/Queen Mary University of London/REF
pubs.organisational-group/Queen Mary University of London/REF/REF - S&E - EECS UoA11
pubs.publication-statusPublisheden_US
dcterms.dateAccepted2017-07-03en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record