Exploring the feature space of character-level embeddings

Recently, character-level embeddings have become popular in the Natural Language Processing community. These representations provide a description of a word which depends solely on its inner structure, i.e. the sequence of characters. Convolutional and recurrent neural networks are the undisputed protagonists in this context, and they represent the state of the art for many character-level applications. In this work, we firstly compare different neural architectures against adaptive string kernels in simplified scenarios. Then, we propose a hybrid ensemble that injects structural kernel-based features into a neural architecture, providing an efficient and scalable solution. An all-around experimental assessment has been carried out on several string datasets, including biomedical entity recognition and sentiment analysis.