Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance
This work addresses coreference resolution for natural language processing applications, but it appears incremental as it builds on existing neural methods by adding discourse structure.
The paper tackled the problem of entity coreference resolution by incorporating hierarchical discourse representations into a neural model, resulting in significant improvements on two benchmark datasets, though specific numbers are not provided.
Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features. SOTA models do not make use of hierarchical representations of discourse structure. In this work, we leverage automatically constructed discourse parse trees within a neural approach and demonstrate a significant improvement on two benchmark entity coreference-resolution datasets. We explore how the impact varies depending upon the type of mention.