nafyi.
Topics / retrieval methodology

Attributed viewpoint · Not a direct quote

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.

Logan Markewich·Published

Behind the viewpoint

Translations are for reading; original excerpts remain the evidence.

Exploring Static Embedding Retrieval

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.

Additional context is not included in this excerpt. Read the original conversation.

Open original · Paragraph 45 (opens in a new tab)View source page

Open the episode and seek to —.

Text location from the supplied original; confirm wording and attribution in context.