Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test

Philippe Laban, Luke Dai, Lucas Bandarkar, Marti A. Hearst


Abstract
The Shuffle Test is the most common task to evaluate whether NLP models can measure coherence in text. Most recent work uses direct supervision on the task; we show that by simply finetuning a RoBERTa model, we can achieve a near perfect accuracy of 97.8%, a state-of-the-art. We argue that this outstanding performance is unlikely to lead to a good model of text coherence, and suggest that the Shuffle Test should be approached in a Zero-Shot setting: models should be evaluated without being trained on the task itself. We evaluate common models in this setting, such as Generative and Bi-directional Transformers, and find that larger architectures achieve high-performance out-of-the-box. Finally, we suggest the k-Block Shuffle Test, a modification of the original by increasing the size of blocks shuffled. Even though human reader performance remains high (around 95% accuracy), model performance drops from 94% to 78% as block size increases, creating a conceptually simple challenge to benchmark NLP models.
Anthology ID:
2021.acl-short.134
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1058–1064
Language:
URL:
https://aclanthology.org/2021.acl-short.134
DOI:
10.18653/v1/2021.acl-short.134
Bibkey:
Cite (ACL):
Philippe Laban, Luke Dai, Lucas Bandarkar, and Marti A. Hearst. 2021. Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 1058–1064, Online. Association for Computational Linguistics.
Cite (Informal):
Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test (Laban et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.134.pdf
Video:
 https://aclanthology.org/2021.acl-short.134.mp4
Data
BillSum