NEWS.md
perplexity() to asses models’ the goodness-of-fit.textmodel_doc2vec objects.group to as.matrix() to average sentence or paragraph vectors from the same documents.textmodel_doc2vec to train the distributed memory (DM) and distributed bag-of-word (DBOW) models.as.textmodel_doc2vec() to create document vectors as weighted average of word vectors.layer to as.matrix() to choose between word or document vectors.normalize is now defunct in textmodel_word2vec().normalize to textmodel_doc2vec() and pass it to as.matrix().weights to textmodel_doc2vec() to adjust the salience of words in the document vectors.include_data to textmodel_word2vec() to save the original tokens object.model argument to textmodel_word2vec() to update existing models.normalize argument is moved from textmodel_word2vec() to as.matrix(). The original argument is deprecated and set to FALSE by default.weights().tolower argument and set to TRUE to lower-case tokens.x to be quanteda’s tokens_xptr object to enhance efficiency.textmodel_doc2vec objects.textmodel_doc2vec objects.probability() to compute probability of words.word2vec(), doc2vec() and lsa() to textmodel_word2vec(), textmodel_doc2vec() and textmodel_lsa() respectively.normalize to word2vec to disable or enable word vector normalization.weights() to extract back-propagation weights.analogy() to convert a formula to named character vector.word2vec() when verbose = TRUE.word2vec() with new argument names and object structures.lda() to train word vectors using Latent Semantic Analysis.similarity() and analogy() functions using proxyC.data_corpus_news2014 that contain 20,000 news summaries as package data.