
BERTweet
by VinAIResearch (organization)
BERTweet: A pre-trained language model for English Tweets (EMNLP-2020) (description from the project’s GitHub page)
Repository facts
- Stars
- 610
- Forks
- 55
- Open issues and pull requests
- 1
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- VinAIResearch · Organization
- Created
- May 6, 2020
- Last push
- Jul 22, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,036: VinAIResearch/PhoBERT
PhoBERT: Pre-trained language models for Vietnamese (EMNLP-2020 Findings)
809 starsMITLast push Aug 4, 2026
Rank 1,911: JohnSnowLabs/spark-nlp
State of the Art Natural Language Processing
4,160 starsScalaApache-2.0Last push Oct 14, 2026
Rank 6,723: explosion/spacy-streamlit
👑 spaCy building blocks and visualizers for Streamlit apps
863 starsPythonMITLast push Jul 29, 2024
Rank 5,065: 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。
1,307 starsPythonApache-2.0Last push Jun 18, 2022
Rank 3,182: BrikerMan/Kashgari
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embed…
2,381 starsPythonApache-2.0Last push Sep 3, 2024