Use Generalized Representations, But Do Not Forget Surface Features
This work addresses coreference resolution for NLP researchers, but it is incremental as it revisits older methods in light of new paradigms.
The paper tackled the problem of coreference resolution by showing that a simple SVM model with surface features outperforms more complex neural models for detecting anaphoric mentions, achieving better performance in this specific task.
Only a year ago, all state-of-the-art coreference resolvers were using an extensive amount of surface features. Recently, there was a paradigm shift towards using word embeddings and deep neural networks, where the use of surface features is very limited. In this paper, we show that a simple SVM model with surface features outperforms more complex neural models for detecting anaphoric mentions. Our analysis suggests that using generalized representations and surface features have different strength that should be both taken into account for improving coreference resolution.