Package index
-
align_embeddings() - Align Two Embeddings Models
-
average_embedding() - Average Embeddings
-
embed_tokens() - Get Embeddings of Tokens in a Text or Corpus
-
`rownames<-`(<embeddings>)`dimnames<-`(<embeddings>)unique(<embeddings>)t(<embeddings>)rbind(<embeddings>)as.matrix(<embeddings>)as_tibble(<embeddings>) - Methods for Embeddings Objects
-
`[`(<embeddings>)`[<-`(<embeddings>)subset(<embeddings>) - Extract or Subset Parts of Embeddings Objects
-
embeddings()as.embeddings()is.embeddings() - Embeddings Objects
-
find_nearest() - Find Nearest Tokens in Embedding Space
-
format(<embeddings>) - Formatting and Printing for Embeddings Objects
-
get_sims() - Row-wise Similarity and Distance Metrics
-
glove_twitter_25d - 25-d GloVe Model Pretrained on Twitter (subset)
-
load_embeddings() - Load Pretrained GloVe, word2vec, and fastText Embeddings
-
magnitude() - Magnitude of Embeddings
-
normalize()normalize_rows() - Scale Embeddings to the Unit Hypersphere
-
predict(<embeddings>) - Retrieve Token Embeddings
-
project_points_onto_line() - Additional Vector Utilities
-
read_embeddings() - Read Embeddings From a Text or Binary File
-
reduce_dimensionality() - Reduce the Dimensionality of Embeddings
-
sim_matrix() - Pairwise Similarity or Distance Matrix
-
dot_prod()cos_sim()euc_dist()minkowski_dist()anchored_sim() - Similarity and Distance Metrics
-
textstat_embedding()embed_docs() - Get Text Embeddings by Averaging Word Embeddings
-
total_dist()average_sim() - Compare Two Embedding Models