Glyce: Glyph-vectors for Chinese Character Representations
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. Code found at https://github.com/ShannonAI/glyce.
PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract
Tasks
Chinese Dependency Parsing
Chinese Named Entity Recognition
Chinese Part-of-Speech Tagging
Chinese Semantic Role Labeling
Chinese Sentence Pair Classification
Chinese Word Segmentation
Classification
Dependency Parsing
Document Classification
General Classification
Image Classification
Language Modelling
Machine Translation
Multi-Task Learning
NER
Part-Of-Speech Tagging
POS
Semantic Role Labeling
Semantic Textual Similarity
Sentence
Sentence Classification
Sentence-Pair Classification
Sentiment Analysis
text-classification
Text Classification
ImageNet
XNLI
Weibo NER
Resume NER
