Vec2Doc: transforming dense vectors into sparse representations for efficient information retrieval

Conference Paper
Publication Date:
2023
abstract:
Vec2Doc: Transforming Dense Vectors into Sparse Representations for Efficient Information Retrieval
Iris type:
04.01 Contributo in Atti di convegno
Keywords:
Inverted index; Approximate search; High-dimensional indexing; Very large databases; Surrogate text representation
List of contributors:
Authors of the University:
Handle:
https://iris.cnr.it/handle/20.500.14243/439025
Book title:
Similarity Search and Applications