54k lo-fi SVD word-type embeddings from metal lyrics

A matrix of 54,187 word-type vectors (rows) and 20 dimensions (columns). Static word-type embeddings derived from truncated SVD on a distance-weighted term-co-occurrence matrix (TCM) built from the prepped metal lyrics corpus. Each word type has a single vector representation regardless of context.

Format

A matrix of 54,187 rows and 20 columns

Source

Derived from the metal lyrics corpus in text2map.corpora

Examples

if (FALSE) { # \dontrun{

## download the model (once per machine)
download_pretrained("vecs_svd20_metal_type")

## load the model each session
wv <- load_pretrained("vecs_svd20_metal_type")

## check dims
dim(wv) == c(54187, 20)

} # }