search

SeanLee97 / AnglE

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
https://arxiv.org/abs/2309.12871
MIT License
398 stars 30 forks source link

Questions about how to use the model #18

Closed YCaigogogo closed 6 months ago

YCaigogogo commented 6 months ago

Dear author, thank you for your excellent work. I am now looking to measure the semantic similarity between multiple answers generated by a llm and the ground truth answer. Can I directly use your model to extract features from both the answers generated by the large model and the real answer, and then calculate their cosine similarity as the score for their semantic similarity match? Will the performance of STS be affected?

SeanLee97 commented 6 months ago

hi @YCaigogogo , thanks for following our work.

1) You can try to use UAE (non-Retrieval Purposes) to generate features for semantic similarity. 2) Of course, you can use cosine similarity. It will not affect the performance.

YCaigogogo commented 6 months ago

Thank you for reply. I would like to ask what is the max sequence length of UAE?

SeanLee97 commented 6 months ago

@YCaigogogo 512

SeanLee97 commented 6 months ago

i'll close this issue. If you have new problems, you can reopen it.