RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators

TY - UNPB

T1 - RSTGen

T2 - Imbuing Fine-Grained Interpretable Control into Long-FormText Generators

AU - Adewoyin, Rilwan A.

AU - Dutta, Ritabrata

AU - He, Yulan

N1 - NAACL 2022

PY - 2022/5/25

Y1 - 2022/5/25

N2 - 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.

AB - 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.

KW - cs.CL

UR - https://aclanthology.org/2022.naacl-main.133/

U2 - 10.18653/v1/2022.naacl-main.133

DO - 10.18653/v1/2022.naacl-main.133

M3 - Preprint

VL - Proceedings of the NAACL 2022

BT - RSTGen

PB - Association for Computational Linguistics (ACL)

ER -