CLNov 11, 2020
Assessment of text coherence based on the cohesion estimation
arXiv:2011.05788v1
AI Analysis
This work addresses text coherence evaluation for multilingual applications, but it appears incremental as it builds on existing graph-based approaches.
The paper tackles the problem of assessing text coherence by proposing a graph-based method that estimates cohesion, and it demonstrates effectiveness across English, Chinese, and Arabic texts.
In this paper, a graph-based coherence estimation method based on the cohesion estimation is suggested. Our method uses a graph-based approach to provide a user with an understanding of the evaluation process. Moreover, it can be applied to different languages, therefore, the effectiveness of this method is examined on the set of English, Chinese, and Arabic texts.