Paper Info
Title
Glyce: Glyph-vectors for Chinese Character Representations
Abstract
It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found. In this paper, we address this gap by presenting Glyce, the glyph-vectors for Chinese character representations. We make three major innovations: (1) We use historical Chinese scripts (e.g., bronzeware script, seal script, traditional Chinese, etc) to enrich the pictographic evidence in characters; (2) We design CNN structures (called tianzege-CNN) tailored to Chinese character image processing; and (3) We use image-classification as an auxiliary task in a multi-task learning setup to increase the model's ability to generalize. We show that glyph-based models are able to consistently outperform word/char ID-based models in a wide range of Chinese NLP tasks. We are able to set new state-of-the-art results for a variety of Chinese NLP tasks, including tagging (NER, CWS, POS), sentence pair classification, single sentence classification tasks, dependency parsing, and semantic role labeling. For example, the proposed model achieves an F1 score of 80.6 on the OntoNotes dataset of NER, +1.5 over BERT; it achieves an almost perfect accuracy of 99.8% on the Fudan corpus for text classification. (1 2)
Year
Venue
Keywords
2019
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)
language model,semantic role labeling,text classification,dependency parsing,bronzeware script,seal script,traditional chinese
Field
DocType
Volume
Glyph,Computer science,Natural language processing,Artificial intelligence,Machine learning
Conference
32
ISSN
Citations 
PageRank 
1049-5258
0
0.34
References 
Authors
0
10
Name
Order
Citations
PageRank
Yuxian Meng106.08
Wu, Wei200.34
Wang, Fei300.34
Li, Xiaoya402.37
Nie, Ping500.34
Yin, Fan600.34
Li, Muyu700.34
Han, Qinghong801.69
Xiaofei Sun941.10
Jiwei Li10102848.05