Year: 2016
Type: conference-paper
Abstract: We discuss an approximate similarity search for word embeddings, which is an operation to approximately find embeddings close to a given vector.We compared several metric-based search algorithms with hash-, tree-, and graphbased indexing from different aspects.Our experimental results showed that a graph-based indexing exhibits robust performance and additionally provided useful information, e.g., vector normalization achieves an efficient search with cosine similarity.
DOI: 10.18653/v1/p16-1214
Authors: Kohei Sugawara, Hayato Kobayashi, Masajiro Iwasaki
Institution: Yahoo Japan Corp. (Japan)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2511469006