nafyi.Raw static token vectors are a poor fit for MaxSim
Markewich advises against scoring raw static token vectors with MaxSim: it performed worse than standard pooling in the team’s exploration, changes the training target, and assumes contextualized vectors that static embeddings do not provide.
Supporting evidence
Original excerpt
Don't score raw static token vectors with MaxSim. It's worse than the standard pooling, the scoring method is technically changing the training target. MaxSim assumes contextualized vectors and static embeddings are not contextual.Exploring Static Embedding Retrieval
Additional context is not included in this excerpt. Read the original conversation.
Text location from the supplied original; confirm wording and attribution in context.
Share insightCheck this claim