Glyph-aware Embedding of Chinese Characters

Falcon Dai, Zheng Cai


Abstract
Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character’s glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to incorporate the spatio-structural patterns of Chinese glyphs as rendered in raw pixels. In the context of two basic Chinese NLP tasks of language modeling and word segmentation, the model learns to represent each character’s task-relevant semantic and syntactic information in the character-level embedding.
Anthology ID:
W17-4109
Volume:
Proceedings of the First Workshop on Subword and Character Level Models in NLP
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Manaal Faruqui, Hinrich Schuetze, Isabel Trancoso, Yadollah Yaghoobzadeh
Venue:
SCLeM
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–69
Language:
URL:
https://aclanthology.org/W17-4109
DOI:
10.18653/v1/W17-4109
Bibkey:
Cite (ACL):
Falcon Dai and Zheng Cai. 2017. Glyph-aware Embedding of Chinese Characters. In Proceedings of the First Workshop on Subword and Character Level Models in NLP, pages 64–69, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Glyph-aware Embedding of Chinese Characters (Dai & Cai, SCLeM 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/W17-4109.pdf
Code
 falcondai/chinese-char-lm