中文版 | English
Title

RSTGen: Imbuing Fine-Grained Interpretable Control into Long-Form Text Generators

Author
Publication Years
2022
Conference Name
Conference of the North-American-Chapter-of-the-Association-for-Computational-Linguistics (NAAACL) - Human Language Technologies
Source Title
Pages
1822-1835
Conference Date
JUL 10-15, 2022
Conference Place
null,Seattle,WA
Publication Place
209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
Publisher
Abstract
In this paper, we study the task of improving the cohesion and coherence of long-form text generated by language models. To this end, we propose RSTGen, a framework that utilises Rhetorical Structure Theory (RST), a classical language theory, to control the discourse structure, semantics and topics of generated text. Firstly, we demonstrate our model's ability to control structural discourse and semantic features of generated text in open generation evaluation. Then we experiment on the two challenging long-form text tasks of argument generation and story generation. Evaluation using automated metrics and a metric with high correlation to human evaluation, shows that our model performs competitively against existing models, while offering significantly more controls over generated text than alternative methods.
SUSTech Authorship
Others
Language
English
URL[Source Record]
Indexed By
Funding Project
Engineering and Physical Sciences Research Council[EP/T017112/1];Engineering and Physical Sciences Research Council[EP/V048597/1];
WOS Research Area
Computer Science ; Linguistics
WOS Subject
Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Linguistics
WOS Accession No
WOS:000859869501068
Scopus EID
2-s2.0-85138371306
Data Source
Scopus
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/402773
DepartmentDepartment of Computer Science and Engineering
Affiliation
1.Department of Computer Science,University of Warwick,United Kingdom
2.Department of Statistics,University of Warwick,United Kingdom
3.The Alan Turing Institute,United Kingdom
4.Department of Computer Science and Engineering,Southern University of Science and Technology,China
First Author AffilicationDepartment of Computer Science and Engineering
Recommended Citation
GB/T 7714
Adewoyin,Rilwan A.,Dutta,Ritabrata,He,Yulan. RSTGen: Imbuing Fine-Grained Interpretable Control into Long-Form Text Generators[C]. 209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA:ASSOC COMPUTATIONAL LINGUISTICS-ACL,2022:1822-1835.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Adewoyin,Rilwan A.]'s Articles
[Dutta,Ritabrata]'s Articles
[He,Yulan]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Adewoyin,Rilwan A.]'s Articles
[Dutta,Ritabrata]'s Articles
[He,Yulan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Adewoyin,Rilwan A.]'s Articles
[Dutta,Ritabrata]'s Articles
[He,Yulan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.