wordemb_FasttextEng_sample {keyclust} | R Documentation |
Sample from the pre-trained English fastText model
Description
This is a data frame containing the 2,000 most frequently occurring terms from Facebook's English-language fastText word embeddings model.
Usage
wordemb_FasttextEng_sample
Format
A 2000 row and 301 column data frame. The row represents the word embedding term, while the numeric columns represent the word embedding dimension. The character column gives the terms associated with each word vector.
References
P. Bojanowski*, E. Grave*, A. Joulin, T. Mikolov, Enriching Word Vectors with Subword Information (arxiv)
Examples
data(wordemb_FasttextEng_sample)
head(wordemb_FasttextEng_sample)
[Package keyclust version 1.2.5 Index]