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

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.

Automated summary

This paper introduces RSTGen, a framework based on Rhetorical Structure Theory (RST), to enhance the cohesion and coherence of long-form text generated by language models. The model demonstrates its ability to control the structural discourse and semantic features of generated text, and performs competitively in argument generation and story generation tasks.