Hashformers v2.0.0 is out! πŸš€

Hashtag segmentation, the task of adding spaces between words in a hashtag, can now be done with Large Language Models (LLMs).

Recognized as the state-of-the-art solution for hashtag segmentation at LREC 2022, hashformers has been utilized in research on social media sentiment analysis and other natural language tasks across numerous languages.

Hashformers v2.0.0 introduces game-changing features for hashtag segmentation:

  • Support for Large Language Models (LLMs) such as GPT-J, Dolly, and Alpaca-LoRA;
  • Additional support for BERT-like and Seq2Seq models, including BERT, DeBERTa, T5, FLAN-T5, and more;
  • Enhanced documentation and customization options now allow you to adapt hashformers to your unique data preprocessing requirements.

Check it out now and star our repo ⭐: https://github.com/ruanchaves/hashformers

Experiment with our hashtag segmentation app on Hugging Face Spaces: https://huggingface.co/spaces/ruanchaves/hashtag-segmentation

--

--

Ruan Chaves Rodrigues

Machine Learning Engineer. MSc student at the EMLCT programme. Personal website: https://ruanchaves.github.io/