i build word2vec network with 2 linear layers from pytorch. for every word as an input i consistently train model to predict words before and after, for example: i was visiting my grandma's house, for the word - "visiting", i train model to predict "was", then to predict "my", etc. But after training my model predicts always the same word, as rule the first training word ("visiting" from my example)

enter image description here



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.