VinAIResearch/BERTweet
BERTweet is a pre-trained BERT-style language model trained on 850M English tweets for NLP tasks like sentiment analysis, NER, and POS tagging.
Not currently ranked — collecting fresh signals.
star history
BERTweet is a pre-trained transformer-based language model developed by VinAI Research. It adapts the RoBERTa pre-training procedure specifically for English tweets, trained on a corpus of 850M English Tweets (including 5M COVID-19 related). The model supports downstream tasks including sentiment analysis, irony detection, named entity recognition, part-of-speech tagging, and text classification. It can be used via both the Hugging Face transformers library and fairseq.
Frequently asked
- What is VinAIResearch/BERTweet?
- BERTweet is a pre-trained BERT-style language model trained on 850M English tweets for NLP tasks like sentiment analysis, NER, and POS tagging.
- Is BERTweet open source?
- Yes — VinAIResearch/BERTweet is open source, released under the MIT license.
- What language is BERTweet written in?
- VinAIResearch/BERTweet is primarily written in Python.
- How popular is BERTweet?
- VinAIResearch/BERTweet has 609 stars on GitHub.
- Where can I find BERTweet?
- VinAIResearch/BERTweet is on GitHub at https://github.com/VinAIResearch/BERTweet.