Words or Characters? Fine-grained Gating for Reading Comprehension
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.
Cite
@article{arxiv.1611.01724,
title = {Words or Characters? Fine-grained Gating for Reading Comprehension},
author = {Zhilin Yang and Bhuwan Dhingra and Ye Yuan and Junjie Hu and William W. Cohen and Ruslan Salakhutdinov},
journal= {arXiv preprint arXiv:1611.01724},
year = {2017}
}
Comments
Accepted as a conference paper at ICLR 2017