Exciting news from @SemanticScholar! Introducing SPECTER2, the adaptable upgrade to SPECTER. Learn about its advanced features and SciRepEval, the new benchmark for scientific document embeddings. Check it out: https://t.co/I7PZWZLWQC #EMNLP2023
Training and inference with language models is expensive. ♻️Embedding recycling♻️can preserve SOTA performance while improving efficiency.
Preprint with Amanpreet Singh, @soldni, Mike D’Arcy, @armancohan, and @_DougDowney: https://t.co/fFVBMjeJOH, https://t.co/9osTBWi9ED