Learning Chinese Word Representations From Glyphs Of Characters

TL;DR

This paper introduces novel methods to enhance Chinese word representations by leveraging character glyphs learned from bitmaps using convolutional auto-encoders, and provides new evaluation datasets for traditional Chinese.

Contribution

It presents a new approach combining glyph features with character embeddings to improve Chinese word representations and releases publicly available evaluation datasets.

Findings

Glyph features improve word representations

Character glyphs learned from bitmaps enhance semantic understanding

New evaluation datasets for traditional Chinese are provided

Abstract

In this paper, we propose new methods to learn Chinese word representations. Chinese characters are composed of graphical components, which carry rich semantics. It is common for a Chinese learner to comprehend the meaning of a word from these graphical components. As a result, we propose models that enhance word representations by character glyphs. The character glyph features are directly learned from the bitmaps of characters by convolutional auto-encoder(convAE), and the glyph features improve Chinese word representations which are already enhanced by character embeddings. Another contribution in this paper is that we created several evaluation datasets in traditional Chinese and made them public.