Gating Mechanisms for Combining Character and Word-level Word Representations: An Empirical Study

Abstract

In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the learned representations at the word and sentence levels, and that doing so is particularly useful when representing less frequent words. We further show that a feature-wise sigmoid gating mechanism is a robust method for creating representations that encode semantic similarity, as it performed reasonably well in several word similarity datasets. Finally, our findings suggest that properly capturing semantic similarity at the word level does not consistently yield improved performance in downstream sentence-level tasks. Our code is available at https://github.com/jabalazs/gating

Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop

References in corpus (5)

• Skip-Thought Vectors
• Compositional Morphology for Word Representations and Language Modelling
• No Training Required: Exploring Random Encoders for Sentence Classification
• Self-Adaptive Hierarchical Sentence Model
• How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks