Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-30966
Title: | A Hybrid Model for Globally Coherent Story Generation |
Author(s): | Zhai, Fangzhou Demberg, Vera Shkadzko, Pavel Shi, Wei Sayeed, Asad |
Editor(s): | Ferraro, Francis |
Language: | English |
Title: | Storytelling - proceedings of the second workshop : August 1, 2019, Florence, Italy : ACL 2019 |
Startpage: | 34 |
Endpage: | 45 |
Publisher/Platform: | ACL |
Year of Publication: | 2019 |
Place of publication: | Stroudsburg, PA |
Title of the Conference: | Storytelling Workshop 2019 |
Place of the conference: | Florence, Italy |
Publikation type: | Conference Paper |
Abstract: | Automatically generating globally coherent stories is a challenging problem. Neural text generation models have been shown to perform well at generating fluent sentences from data, but they usually fail to keep track of the overall coherence of the story after a couple of sentences. Existing work that incorporates a text planning module succeeded in generating recipes and dialogues, but appears quite data-demanding. We propose a novel story generation approach that generates globally coherent stories from a fairly small corpus. The model exploits a symbolic text planning module to produce text plans, thus reducing the demand of data; a neural surface realization module then generates fluent text conditioned on the text plan. Human evaluation showed that our model outperforms various baselines by a wide margin and generates stories which are fluent as well as globally coherent. |
DOI of the first publication: | 10.18653/v1/W19-3404 |
URL of the first publication: | https://www.aclweb.org/anthology/W19-3404/ |
Link to this record: | hdl:20.500.11880/29737 http://dx.doi.org/10.22028/D291-30966 |
ISBN: | 978-1-950737-44-4 |
Date of registration: | 24-Sep-2020 |
Faculty: | MI - Fakultät für Mathematik und Informatik |
Department: | MI - Informatik |
Professorship: | MI - Prof. Dr. Vera Demberg |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.