# Use Generalized Representations, But Do Not Forget Surface Features

## TL;DR

This paper demonstrates that traditional surface features, when combined with generalized representations, can outperform neural models in coreference resolution, highlighting the importance of integrating both approaches.

## Contribution

It shows that simple models with surface features can outperform complex neural models, emphasizing the value of surface features alongside generalized representations.

## Key findings

- Surface features improve coreference resolution performance.
- Simple SVM with surface features outperforms neural models.
- Combining generalized representations and surface features is beneficial.

## Abstract

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.