#109 · Primary category： Foundation Models
BERTweet
BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)
Project last updated：07/22/24
GitHub Stars
609
Forks
55
Contributors
2
License
MIT
Why we included this project
BERTweet is a RoBERTa-style model pre-trained on roughly 850 million tweets, so it's built for the abbreviations, emoji, and URL-heavy text that standard BERT models tend to choke on. The tokenizer and normalization step are designed for that input, and the repo includes a TweetNormalizer module to get your raw tweets into the right format. You can load the base or large checkpoints through the Hugging Face transformers API and fine-tune them for sentiment analysis, named-entity recognition, part-of-speech tagging, or irony detection. That makes it a practical starting point for social listening, brand monitoring, or any analysis of public conversation.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities