ruimtehol (version 0.3.2)

embed_articlespace: Build a Starspace model for learning the mapping between sentences and articles (articlespace)

Description

Build a Starspace model for learning the mapping between sentences and articles (articlespace)

Usage

embed_articlespace(
  x,
  model = "articlespace.bin",
  early_stopping = 0.75,
  useBytes = FALSE,
  ...
)

Value

an object of class textspace as returned by starspace.

Arguments

x

a data.frame with sentences containing the columns doc_id, sentence_id and token The doc_id is just an article or document identifier, the sentence_id column is a character field which contains words which are separated by a space and should not contain any tab characters

model

name of the model which will be saved, passed on to starspace

early_stopping

the percentage of the data that will be used as training data. If set to a value smaller than 1, 1-early_stopping percentage of the data which will be used as the validation set and early stopping will be executed. Defaults to 0.75.

useBytes

set to TRUE to avoid re-encoding when writing out train and/or test files. See writeLines for details

...

further arguments passed on to starspace except file, trainMode and fileFormat

Examples

if(require(udpipe)){
library(udpipe)
data(brussels_reviews_anno, package = "udpipe")
x <- subset(brussels_reviews_anno, language == "nl")
x$token <- x$lemma
x <- x[, c("doc_id", "sentence_id", "token")]
set.seed(123456789)
model <- embed_articlespace(x, early_stopping = 1,
                            dim = 25, epoch = 25, minCount = 2,
                            negSearchLimit = 1, maxNegSamples = 2)
plot(model)
sentences <- c("ook de keuken zijn zeer goed uitgerust .",
               "het appartement zijn met veel smaak inrichten en zeer proper .")
predict(model, sentences, type = "embedding")
starspace_embedding(model, sentences)
} # End of main if statement running only if the required packages are installed
if (FALSE) {
library(udpipe)
data(dekamer, package = "ruimtehol")
dekamer <- subset(dekamer, question_theme_main == "DEFENSIEBELEID")
x <- udpipe(dekamer$question, "dutch", tagger = "none", parser = "none", trace = 100)
x <- x[, c("doc_id", "sentence_id", "sentence", "token")]
set.seed(123456789)
model <- embed_articlespace(x, early_stopping = 0.8, dim = 15, epoch = 5, minCount = 5)
plot(model)

embeddings <- starspace_embedding(model, unique(x$sentence), type = "document")
dim(embeddings)

sentence <- "Wat zijn de cijfers qua doorstroming van 2016?"
embedding_sentence <- starspace_embedding(model, sentence, type = "document")
mostsimilar <- embedding_similarity(embeddings, embedding_sentence)
head(sort(mostsimilar[, 1], decreasing = TRUE), 3)

## clean up for cran
file.remove(list.files(pattern = ".udpipe$"))
}