DeepAI AI Chat
Log In Sign Up

Analyzing Neural Discourse Coherence Models

by   Youmna Farag, et al.

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test model sensitivity to changes in syntax and semantics. We furthermore probe discourse embedding space and examine the knowledge that is encoded in representations of coherence. We hope this study shall provide further insight into how to frame the task and improve models of coherence assessment further. Finally, we make our datasets publicly available as a resource for researchers to use to test discourse coherence models.


page 1

page 2

page 3

page 4


Neural Net Models for Open-Domain Discourse Coherence

Discourse coherence is strongly associated with text quality, making it ...

Towards Modelling Coherence in Spoken Discourse

While there has been significant progress towards modelling coherence in...

Modeling Topical Coherence in Discourse without Supervision

Coherence of text is an important attribute to be measured for both manu...

Investigating the Role of Centering Theory in the Context of Neural Coreference Resolution Systems

Centering theory (CT; Grosz et al., 1995) provides a linguistic analysis...

Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference

Performing event and entity coreference resolution across documents vast...

Tracking Discourse Influence in Darknet Forums

This technical report documents our efforts in addressing the tasks set ...