wordvector: word and document vector models

How to install

install.packages("wordvector")

remotes::install_github("koheiw/wordvector")

Example

Download data

# download data
download.file('https://www.dropbox.com/s/e19kslwhuu9yc2z/yahoo-news.RDS?dl=1', 
 '~/yahoo-news.RDS', mode = "wb")

Train word2vec

library(wordvector)
library(quanteda)
## Package version: 4.5.0.9000
## Unicode version: 15.1
## ICU version: 74.1
## Parallel computing: 16 of 16 threads used.
## See https://quanteda.io for tutorials and examples.
# Load data
dat <- readRDS('~/yahoo-news.RDS')
dat$text <- paste0(dat$head, ". ", dat$body)
corp <- corpus(dat, text_field = 'text', docid_field = "tid")
# Pre-processing
toks <- tokens(corp, remove_punct = TRUE, remove_symbols = TRUE) %>% 
 tokens_remove(stopwords("en", "marimo"), padding = TRUE) %>% 
 tokens_select("^[a-zA-Z-]+$", valuetype = "regex", case_insensitive = FALSE,
 padding = TRUE)
# Train word2vec
wov <- textmodel_word2vec(toks, dim = 50, type = "cbow", min_count = 5, verbose = TRUE)
## Training continuous BOW model with 50 dimensions
## ...using 16 threads for distributed computing
## ...initializing
## ...negative sampling in 10 iterations
## ......iteration 1 elapsed time: 6.14 seconds (alpha: 0.0455)
## ......iteration 2 elapsed time: 12.83 seconds (alpha: 0.0409)
## ......iteration 3 elapsed time: 18.90 seconds (alpha: 0.0364)
## ......iteration 4 elapsed time: 25.03 seconds (alpha: 0.0320)
## ......iteration 5 elapsed time: 31.32 seconds (alpha: 0.0275)
## ......iteration 6 elapsed time: 37.58 seconds (alpha: 0.0230)
## ......iteration 7 elapsed time: 45.09 seconds (alpha: 0.0183)
## ......iteration 8 elapsed time: 51.82 seconds (alpha: 0.0139)
## ......iteration 9 elapsed time: 58.50 seconds (alpha: 0.0095)
## ......iteration 10 elapsed time: 65.41 seconds (alpha: 0.0049)
## ...complete

Similarity between word vectors

head(similarity(wov, c("amazon", "forests", "obama", "america", "afghanistan"), 
 mode = "character"))
## amazon forests obama america afghanistan 
## [1,] "amazon" "forests" "obama" "america" "afghanistan"
## [2,] "peatlands" "herds" "barack" "dakota" "afghan" 
## [3,] "rainforest" "rainforest" "biden" "american" "kabul" 
## [4,] "soy" "farmland" "kerry" "carolina" "taliban" 
## [5,] "zijin" "grasslands" "hagel" "africa" "pakistan" 
## [6,] "warm-water" "forest" "clinton" "america-focused" "afghans"

Arithmetic operations of word vectors

# What is Amazon without forests?
head(similarity(wov, analogy(~ amazon - forests))) 
## [,1] 
## [1,] "smash-hit" 
## [2,] "activision" 
## [3,] "iovine" 
## [4,] "nbcuniversal"
## [5,] "telephony" 
## [6,] "pandora"

# What is for Afghanistan as Obama for America? 
head(similarity(wov, analogy(~ obama - america + afghanistan))) 
## [,1] 
## [1,] "afghanistan"
## [2,] "taliban" 
## [3,] "afghan" 
## [4,] "karzai" 
## [5,] "obama" 
## [6,] "nato"

# What is for France as Berlin for Germany?
head(similarity(wov, analogy(~ berlin - germany + france))) 
## [,1] 
## [1,] "paris" 
## [2,] "berlin" 
## [3,] "brussels"
## [4,] "london" 
## [5,] "france" 
## [6,] "kourou"

# What is for slowly as quick for quickly?
head(similarity(wov, analogy(~ quick - quickly + slowly)))
## [,1] 
## [1,] "fades" 
## [2,] "pitching" 
## [3,] "uneven" 
## [4,] "earlier-than-expected"
## [5,] "sideways" 
## [6,] "bumpy"