Sean Lee
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring specialized training or supervision.
The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring specialized training or supervision.
Papers
Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…