A Unified Neural Coherence Model
This addresses the problem of improving coherence modeling for applications like dialogue and translation, though it appears incremental as it builds on existing neural approaches.
The paper tackled the problem of neural coherence models failing on harder tasks requiring local context sensitivity, such as in conversational dialogue and machine translation, by proposing a unified model that incorporates sentence grammar, inter-sentence coherence relations, and global patterns, and demonstrated it outperforms existing models by a good margin, establishing a new state-of-the-art.
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.