kipi-ai/korpatelectra
특허분야 특화된 한국어 AI언어모델 KorPatELECTRA
This is an AI language model specifically trained on a vast collection of Korean patent documents. It takes raw Korean patent text as input and outputs processed language data, which can then be used to improve tasks like identifying key entities, classifying patents, or answering questions related to patent information. Patent attorneys, IP researchers, and patent analysts would find this useful for enhancing their Korean patent processing workflows.
No commits in the last 6 months.
Use this if you need to perform natural language processing tasks on Korean patent documents and require a highly specialized language model for improved accuracy.
Not ideal if your work involves general Korean text rather than patent-specific language, or if you need a language model for a domain other than patents.
Stars
8
Forks
4
Language
—
License
—
Category
Last pushed
Jan 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kipi-ai/korpatelectra"
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.