# Words or Characters? Fine-grained Gating for Reading Comprehension

arXiv: https://arxiv.org/abs/1611.01724 · HTML: https://mlsanity.com/paper/1611.01724/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2016.

## Built on by (most cited first, 3 of 3)

- [Generative Language Models for Paragraph-Level Question Generation](https://mlsanity.com/paper/2210.03992/) (2022)
- [Do Question Answering Modeling Improvements Hold Across Benchmarks?](https://mlsanity.com/paper/2102.01065/) (2021)
- [Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization](https://mlsanity.com/paper/2110.04741/) (2021)

## Abstract (arXiv)

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.