Controllable Neural Story Plot Generation via Reward Shaping

Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story. LM techniques lack the ability to receive guidance from the user to achieve a specific goal, resulting...

Full description

Saved in:

Bibliographic Details
Published in:	arXiv.org
Main Authors:	Tambwekar, Pradyumna, Dhuliawala, Murtaza, Martin, Lara J, Mehta, Animesh, Harrison, Brent, Riedl, Mark O
Format:	Paper
Language:	English
Published:	Ithaca Cornell University Library, arXiv.org 18.01.2023
Subjects:	Controllability
ISSN:	2331-8422
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story. LM techniques lack the ability to receive guidance from the user to achieve a specific goal, resulting in stories that don't have a clear sense of progression and lack coherence. We present a reward-shaping technique that analyzes a story corpus and produces intermediate rewards that are backpropagated into a pre-trained LM in order to guide the model towards a given goal. Automated evaluations show our technique can create a model that generates story plots which consistently achieve a specified goal. Human-subject studies show that the generated stories have more plausible event ordering than baseline plot generation techniques.
Bibliography:	SourceType-Working Papers-1 ObjectType-Working Paper/Pre-Print-1 content type line 50
ISSN:	2331-8422
DOI:	10.48550/arxiv.1809.10736