TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Coherence Evaluation	GCDC + RST - Accuracy	ParSeq	Accuracy	55.09	# 3
Coherence Evaluation	GCDC + RST - F1	ParSeq	Average F1	46.65	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/discourse-coherence-in-the-wild-a-dataset/coherence-evaluation-on-gcdc-rst-f1)](https://paperswithcode.com/sota/coherence-evaluation-on-gcdc-rst-f1?p=discourse-coherence-in-the-wild-a-dataset)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/discourse-coherence-in-the-wild-a-dataset/coherence-evaluation-on-gcdc-rst-accuracy)](https://paperswithcode.com/sota/coherence-evaluation-on-gcdc-rst-accuracy?p=discourse-coherence-in-the-wild-a-dataset)`

Discourse Coherence in the Wild: A Dataset, Evaluation and Methods

WS 2018 · Alice Lai, Joel Tetreault ·

To date there has been very little work on assessing discourse coherence methods on real-world data. To address this, we present a new corpus of real-world texts (GCDC) as well as the first large-scale evaluation of leading discourse coherence algorithms. We show that neural models, including two that we introduce here (SentAvg and ParSeq), tend to perform best. We analyze these performance differences and discuss patterns we observed in low coherence texts in four domains.