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

Adewoyin，Rilwan A.1,4; Dutta，Ritabrata2; He，Yulan1,3

2022

Conference of the North-American-Chapter-of-the-Association-for-Computational-Linguistics (NAAACL) - Human Language Technologies

NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

1822-1835

JUL 10-15, 2022

null,Seattle,WA

209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA

ASSOC COMPUTATIONAL LINGUISTICS-ACL

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.

Others

English

CPCI-S ; CPCI-SH

Engineering and Physical Sciences Research Council[EP/T017112/1];Engineering and Physical Sciences Research Council[EP/V048597/1];

Computer Science ; Linguistics

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Linguistics

WOS:000859869501068

2-s2.0-85138371306

Scopus

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

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.