I am fairly new to the NLP embedding world. I used gensim's word2vec model and tensorflow vector representation.
I have a question that while training gensim's word2vec model it takes tokenize sentences, while tensorflow takes a long list of words. How does it differ in training. Is there any quality impact? Also how does then tensorflow cater to the needs of skip-gram as now the data is a list of words and no more sentences. I am referring to the tensorflow's tutorial found at link https://www.tensorflow.org/tutorials/word2vec
Pardon me if my understanding in this domain is wrong would appreciate if my understanding is cleared.
Thank you for your guidance and help.