Learning Chinese Word Representations From Glyphs Of Characters
Journal
EMNLP
Pages
162
Date Issued
2017
Author(s)
Tzu-Ray Su
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. © 2017 Association for Computational Linguistics.
Other Subjects
Semantics; Auto encoders; Bit maps; Chinese characters; Word representations; Natural language processing systems
Type
conference paper