Words or Characters? Fine-grained Gating for Reading Comprehension

TL;DR

This paper introduces a dynamic fine-grained gating mechanism to better combine word and character representations, significantly improving reading comprehension performance and generalizing to other NLP tasks.

Contribution

The paper proposes a novel fine-grained gating method for integrating word and character features, enhancing reading comprehension models and demonstrating broad applicability.

Findings

Achieves state-of-the-art results on the Children's Book Test dataset.

Improves social media tag prediction performance.

Outperforms previous methods in combining word and character representations.

Abstract

Previous work combines word-level and character-level representations using concatenation or scalar weighting, which is suboptimal for high-level tasks like reading comprehension. We present a fine-grained gating mechanism to dynamically combine word-level and character-level representations based on properties of the words. We also extend the idea of fine-grained gating to modeling the interaction between questions and paragraphs for reading comprehension. Experiments show that our approach can improve the performance on reading comprehension tasks, achieving new state-of-the-art results on the Children's Book Test dataset. To demonstrate the generality of our gating mechanism, we also show improved results on a social media tag prediction task.