Joint Modeling of Entities and Discourse Relations for Coherence Assessment
This work addresses coherence evaluation in linguistics, offering an incremental improvement by combining existing features for better performance.
The paper tackled the problem of coherence assessment by jointly modeling entities and discourse relations, which are typically handled separately, and found that integrating both features significantly enhances model performance on three benchmark datasets.
In linguistics, coherence can be achieved by different means, such as by maintaining reference to the same set of entities across sentences and by establishing discourse relations between them. However, most existing work on coherence modeling focuses exclusively on either entity features or discourse relation features, with little attention given to combining the two. In this study, we explore two methods for jointly modeling entities and discourse relations for coherence assessment. Experiments on three benchmark datasets show that integrating both types of features significantly enhances the performance of coherence models, highlighting the benefits of modeling both simultaneously for coherence evaluation.