Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks

Tasnim Mohiuddin, Prathyusha Jwalapuram, Xiang Lin, Shafiq Joty


Abstract
Although coherence modeling has come a long way in developing novel models, their evaluation on downstream applications for which they are purportedly developed has largely been neglected. With the advancements made by neural approaches in applications such as machine translation (MT), summarization and dialog systems, the need for coherence evaluation of these tasks is now more crucial than ever. However, coherence models are typically evaluated only on synthetic tasks, which may not be representative of their performance in downstream applications. To investigate how representative the synthetic tasks are of downstream use cases, we conduct experiments on benchmarking well-known traditional and neural coherence models on synthetic sentence ordering tasks, and contrast this with their performance on three downstream applications: coherence evaluation for MT and summarization, and next utterance prediction in retrieval-based dialog. Our results demonstrate a weak correlation between the model performances in the synthetic tasks and the downstream applications, motivating alternate training and evaluation methods for coherence models.
Anthology ID:
2021.eacl-main.308
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3528–3539
Language:
URL:
https://aclanthology.org/2021.eacl-main.308
DOI:
10.18653/v1/2021.eacl-main.308
Bibkey:
Cite (ACL):
Tasnim Mohiuddin, Prathyusha Jwalapuram, Xiang Lin, and Shafiq Joty. 2021. Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3528–3539, Online. Association for Computational Linguistics.
Cite (Informal):
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks (Mohiuddin et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.308.pdf