Select and aggregate layers of hidden states to form a word embedding.

Select and aggregate layers of hidden states to form a word embedding.

textEmbedLayerAggregation(
  word_embeddings_layers,
  layers = "all",
  aggregation_from_layers_to_tokens = "concatenate",
  aggregation_from_tokens_to_texts = "mean",
  return_tokens = FALSE,
  tokens_select = NULL,
  tokens_deselect = NULL
)

Arguments

word_embeddings_layers

Layers returned by the textEmbedRawLayers function.

layers

(character or numeric) The numbers of the layers to be aggregated (e.g., c(11:12) to aggregate the eleventh and twelfth). Note that layer 0 is the input embedding to the transformer, and should normally not be used. Selecting 'all' thus removes layer 0 (default = "all")

aggregation_from_layers_to_tokens

(character) Method to carry out the aggregation among the layers for each word/token, including "min", "max" and "mean" which takes the minimum, maximum or mean across each column; or "concatenate", which links together each layer of the word embedding to one long row (default = "concatenate").

aggregation_from_tokens_to_texts

(character) Method to carry out the aggregation among the word embeddings for the words/tokens, including "min", "max" and "mean" which takes the minimum, maximum or mean across each column; or "concatenate", which links together each layer of the word embedding to one long row (default = "mean").

return_tokens

(boolean) If TRUE, provide the tokens used in the specified transformer model (default = FALSE).

tokens_select

(character) Option to only select embeddings linked to specific tokens such as "[CLS]" and "[SEP]" (default NULL).

tokens_deselect

(character) Option to deselect embeddings linked to specific tokens such as "[CLS]" and "[SEP]" (default NULL).

Value

A tibble with word embeddings. Note that layer 0 is the input embedding to the transformer, which is normally not used.

See also

See textEmbedRawLayers and textEmbed.

Examples

#Aggregate the hidden states from textEmbedRawLayers
#to create a word embedding representing the entire text.
#This is achieved by concatenating layer 11 and 12.
if (FALSE) {
word_embedding <- textEmbedLayerAggregation(
                    imf_embeddings_11_12$context_tokens,
                    layers = 11:12,
                    aggregation_from_layers_to_tokens = "concatenate",
                    aggregation_from_tokens_to_texts = "mean"
)

#Examine word_embedding
word_embedding
}