Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Similarity Learning lacks a framework. So we built one. Parent comment
Basically, you can collect text from different authors, then you can use authors names as labels to train a similarity learning with it. My suggestion would be finetune a Transformer model with a specific head and an ArcFace loss.
There are no comments on this comment yet.
Basically, you can collect text from different authors, then you can use authors names as labels to train a similarity learning with it. My suggestion would be finetune a Transformer model with a specific head and an ArcFace loss.