relbert

RelBERT is a high-quality semantic representative embedding of word pairs powered by pre-trained language model. Install relbert via pip,

   
      pip install relbert
   

and play with RelBERT models.

   
      from relbert import RelBERT
      model = RelBERT('relbert/relbert-roberta-large')
      vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (1024, )
   

See more information bellow.

•   - GitHub: https://github.com/asahi417/relbert
•   - Paper (EMNLP 2021 main conference): https://arxiv.org/abs/2110.15705
•   - HuggingFace: https://huggingface.co/relbert
•   - PyPI: https://pypi.org/project/relbert