word2vec: Pre-trained Word2vec Dataset from Corpus

In softmaxreg: Training Multi-Layer Neural Network for Softmax Regression and Classification

Description

This dataset is a small pre-trained word2vec dataset with 20 dimensions and 5296 words.

Usage

data("word2vec")

Format

A data frame with 12853 observations on the following 21 variables.

word

character

col1

numeric

col2

numeric

col3

numeric

col4

numeric

col5

numeric

col6

numeric

col7

numeric

col8

numeric

col9

numeric

col10

numeric

col11

numeric

col12

numeric

col13

numeric

col14

numeric

col15

numeric

col16

numeric

col17

numeric

col18

numeric

col19

numeric

col20

numeric

Source

Reuter_50_50 dataset,UCI Machine Learning Repository[https://archive.ics.uci.edu/ml/datasets/Reuter_50_50]

References

word2vec model are trained based on below text corpus:

Reuter_50_50 dataset,UCI Machine Learning Repository[https://archive.ics.uci.edu/ml/datasets/Reuter_50_50], Author: Zhi Liu, National Engineering Research Center For E-Learning Technology, Hubei Wuhan, China

Examples

data(word2vec)

Example output

softmaxreg documentation built on May 2, 2019, 6:08 a.m.