Dual Long Short-Term Memory Networks for Sub-Character Representation Learning

@article{He2017DualLS,
  title={Dual Long Short-Term Memory Networks for Sub-Character Representation Learning},
  author={Han He and Xiaokun Yang and Lei Wu and Hua Yan and Zhimin Gao and Yi Feng and George Townsend},
  journal={CoRR},
  year={2017},
  volume={abs/1712.08841}
}
Characters have commonly been regarded as the minimal processing unit in Natural Language Processing (NLP). But many non-latin languages have hieroglyphic writing systems, involving a big alphabet with thousands or millions of characters. Each character is composed of even smaller parts, which are often ignored by the previous work. In this paper, we propose a novel architecture employing two stacked Long Short-Term Memory Networks (LSTMs) to learn sub-character level representation and capture… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 15 times over the past 90 days. VIEW TWEETS