Analyzing Neural Discourse Coherence Models

Youmna Farag, Josef Valvoda, Helen Yannakoudakis, Ted Briscoe


Abstract
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.
Anthology ID:
2020.codi-1.11
Volume:
Proceedings of the First Workshop on Computational Approaches to Discourse
Month:
November
Year:
2020
Address:
Online
Venues:
CODI | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
102–112
Language:
URL:
https://www.aclweb.org/anthology/2020.codi-1.11
DOI:
10.18653/v1/2020.codi-1.11
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.codi-1.11.pdf