# Learning Chinese Word Representations From Glyphs Of Characters

arXiv: https://arxiv.org/abs/1708.04755 · HTML: https://mlsanity.com/paper/1708.04755/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2017.

## Built on by (most cited first, 8 of 8)

- [ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information](https://mlsanity.com/paper/2106.16038/) (2021)
- [On the Emergence of Linear Analogies in Word Embeddings](https://mlsanity.com/paper/2505.18651/) (2025)
- [Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings](https://mlsanity.com/paper/2505.24341/) (2025)
- [GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph](https://mlsanity.com/paper/2107.00395/) (2021)
- [MFE-NER: Multi-feature Fusion Embedding for Chinese Named Entity Recognition](https://mlsanity.com/paper/2109.07877/) (2021)
- [SexWEs: Domain-Aware Word Embeddings via Cross-lingual Semantic Specialisation for Chinese Sexism Detection in Social Media](https://mlsanity.com/paper/2211.08447/) (2022)
- [Shuo Wen Jie Zi: Rethinking Dictionaries and Glyphs for Chinese Language Pre-training](https://mlsanity.com/paper/2305.18760/) (2023)
- [An Evaluation Dataset for Legal Word Embedding: A Case Study On Chinese Codex](https://mlsanity.com/paper/2203.15173/) (2022)

## Abstract (arXiv)

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.