ShannonAI/glyce
Code for NeurIPS 2019 - Glyce: Glyph-vectors for Chinese Character Representations
This project improves the accuracy of natural language processing tasks involving Chinese text. By incorporating the visual appearance (glyphs) of Chinese characters, it enhances how computers understand Chinese words and sentences. It's especially useful for researchers and data scientists working with Chinese language data who need more precise results in tasks like naming entities, tagging parts-of-speech, or classifying sentences.
425 stars. No commits in the last 6 months.
Use this if you need to achieve state-of-the-art performance in various Chinese natural language processing tasks, particularly when working with complex character structures or when existing models struggle with nuance.
Not ideal if your primary focus is on languages other than Chinese, or if you require a lightweight solution for simpler text processing without the overhead of glyph-based models.
Stars
425
Forks
72
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ShannonAI/glyce"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
JayYip/m3tl
BERT for Multitask Learning
920232796/bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
sileod/tasknet
Easy modernBERT fine-tuning and multi-task learning
graykode/toeicbert
TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.