Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.
A Unified Neural Coherence Model
Han-Cheol Moon*, Tasnim Mohiuddin*, Shafiq Joty*, and Chi Xu. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP'19) , pages xx–-xx, 2019.
PDF Abstract BibTex Slides