Read argument
Read argument
Argument Array
Argument Key
Default value of this argument
Value of this key.
Collect frequent words with count >= Threshold
Collect frequent words with count >= Threshold
Word seq.
HashSet of frequent words.
Main thread.
Main thread.
CLI arguments
Convert tokenized string into a sentence, with appropriate conversion of (Threshold - 1) count word.
Convert tokenized string into a sentence, with appropriate conversion of (Threshold - 1) count word.
Tokenized input sentence
Less Frequent words
Tokenized converted sentence
Convert input into tokenized string, using Stanford NLP toolkit.
Convert input into tokenized string, using Stanford NLP toolkit.
Input lines
tokenized & normalized lines.
Train Word2Vec and save the model.