Consider a neural language model based on the following simple feedforward 2-layer network. Assume we're using a context window of 1. That is we're predicting the next word solely from the current one x h=WX = Uh y = softmax(2) Assume we have a vocabulary of size 10,000, hidden layer size 50, and word embeddings of size 300. What are the dimensions of the W and U weight matrices. W is U is