Learning sentence embeddings by Natural Language Inference
Published in
5 min readOct 13, 2018
Unsupervised learning approach seems like a normal way to build word, sentence or document embeddings because it is more generalized such that pre-trained embeddings result can be transfer to other NLP downstream problems. For example, skip-gram in word embeddings and skip-though in sentence embeddings and distributed bag-of-words in paragraph embeddings.