Learning Chinese Word Representations From Glyphs Of Characters

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.

References in corpus (4)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• From Frequency to Meaning: Vector Space Models of Semantics
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Component-Enhanced Chinese Character Embeddings

Cited by in corpus (7)

• Glyce: Glyph-vectors for Chinese Character Representations
• Analogical Reasoning on Chinese Morphological and Semantic Relations
• Chinese Embedding via Stroke and Glyph Information: A Dual-channel View
• Using Chinese Glyphs for Named Entity Recognition
• End-to-End Text Classification via Image-based Embedding using Character-level Networks
• Super Characters: A Conversion from Sentiment Classification to Image Classification
• VCWE: Visual Character-Enhanced Word Embeddings