compute_contrast {conText}

Compute similarity and similarity ratios

Description

Compute similarity and similarity ratios

Usage

compute_contrast(
  target_embeddings1 = NULL,
  target_embeddings2 = NULL,
  pre_trained = NULL,
  candidates = NULL,
  norm = NULL
)

Arguments

target_embeddings1

ALC embeddings for group 1

target_embeddings2

ALC embeddings for group 2

pre_trained

a V x D matrix of numeric values - pretrained embeddings with V = size of vocabulary and D = embedding dimensions

candidates

character vector defining the candidates for nearest neighbors - e.g. output from get_local_vocab

norm

character = c("l2", "none") - set to 'l2' for cosine similarity and to 'none' for inner product (see ?sim2 in text2vec)

Value

a list with three elements, nns for group 1, nns for group 2 and nns_ratio comparing with ratios of similarities between the two groups