Radical-Enhanced Chinese Character Embedding

TL;DR

This paper introduces a novel neural method that incorporates radical information to improve Chinese character embeddings, enhancing performance in character similarity and word segmentation tasks.

Contribution

It is the first to explicitly leverage radicals in neural embeddings for Chinese characters, filling a gap in existing methods.

Findings

Radical-enhanced embeddings outperform existing models in similarity tasks.

The method improves Chinese word segmentation accuracy.

Radical information significantly benefits Chinese NLP tasks.

Abstract

We present a method to leverage radical for learning Chinese character embedding. Radical is a semantic and phonetic component of Chinese character. It plays an important role as characters with the same radical usually have similar semantic meaning and grammatical usage. However, existing Chinese processing algorithms typically regard word or character as the basic unit but ignore the crucial radical information. In this paper, we fill this gap by leveraging radical for learning continuous representation of Chinese character. We develop a dedicated neural architecture to effectively learn character embedding and apply it on Chinese character similarity judgement and Chinese word segmentation. Experiment results show that our radical-enhanced method outperforms existing embedding learning algorithms on both tasks.