Skip to main content
. Author manuscript; available in PMC: 2021 Apr 26.
Published in final edited form as: IEEE J Sel Top Signal Process. 2019 Nov 7;14(2):282–298. doi: 10.1109/jstsp.2019.2952087

Fig. 6:

Fig. 6:

word2vec model architectures proposed in [26]. (a) In the CBOW model, the context words are inputs used to predict the center word. (b) In the skip-gram model, the center word is used to predict the context words.