# Neural RST-based Evaluation of Discourse Coherence

arXiv: https://arxiv.org/abs/2009.14463 · HTML: https://mlsanity.com/paper/2009.14463/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 2 of 2)

- [Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning](https://mlsanity.com/paper/2201.05151/) (2022)
- [Transformer Models for Text Coherence Assessment](https://mlsanity.com/paper/2109.02176/) (2021)

## Abstract (arXiv)

This paper evaluates the utility of Rhetorical Structure Theory (RST) trees and relations in discourse coherence evaluation. We show that incorporating silver-standard RST features can increase accuracy when classifying coherence. We demonstrate this through our tree-recursive neural model, namely RST-Recursive, which takes advantage of the text's RST features produced by a state of the art RST parser. We evaluate our approach on the Grammarly Corpus for Discourse Coherence (GCDC) and show that when ensembled with the current state of the art, we can achieve the new state of the art accuracy on this benchmark. Furthermore, when deployed alone, RST-Recursive achieves competitive accuracy while having 62% fewer parameters.