Learning Global Features for Coreference Resolution
This addresses the challenge of modeling global information in coreference resolution for natural language processing, offering an incremental improvement.
The paper tackled the problem of coreference resolution by learning global features for entity clusters using recurrent neural networks, resulting in a system that outperforms state-of-the-art methods without extra search.
There is compelling evidence that coreference prediction would benefit from modeling global information about entity-clusters. Yet, state-of-the-art performance can be achieved with systems treating each mention prediction independently, which we attribute to the inherent difficulty of crafting informative cluster-level features. We instead propose to use recurrent neural networks (RNNs) to learn latent, global representations of entity clusters directly from their mentions. We show that such representations are especially useful for the prediction of pronominal mentions, and can be incorporated into an end-to-end coreference system that outperforms the state of the art without requiring any additional search.