# Build the bigram and trigram models bigram = gensim.models.Phrases(data_words, min_count=5, threshold=100) # higher threshold fewer phrases. trigram = gensim.models.Phrases(bigram[data_words], threshold=100) # Faster way to get a sentence clubbed as a trigram/bigram bigram_mod = gensim.models.phrases.Phraser(bigram) trigram_mod = gensim.models.phrases.Phraser(trigram)