Learning Chinese Word Representations From Glyphs Of Characters

Tzu-Ray Su, Hung-Yi Lee


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.
Anthology ID:
D17-1025
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
264–273
Language:
URL:
https://aclanthology.org/D17-1025
DOI:
10.18653/v1/D17-1025
Bibkey:
Cite (ACL):
Tzu-Ray Su and Hung-Yi Lee. 2017. Learning Chinese Word Representations From Glyphs Of Characters. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 264–273, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Learning Chinese Word Representations From Glyphs Of Characters (Su & Lee, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1025.pdf
Code
 ray1007/GWE