DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries
Paper • 2405.16153 • Published
How to use RyuKT/DefSentPlus-simcse-bert-base-uncased with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="RyuKT/DefSentPlus-simcse-bert-base-uncased") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("RyuKT/DefSentPlus-simcse-bert-base-uncased")
model = AutoModel.from_pretrained("RyuKT/DefSentPlus-simcse-bert-base-uncased")YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
BibTeX
@misc{liu2024defsent, title={DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries}, author={Xiaodong Liu}, year={2024}, eprint={2405.16153}, archivePrefix={arXiv} }