I read the paper "Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank" recently and was confused with the error function of RNTN parameters, that is equation (2) in part 4.4. As we know, the cross-entropy error should be the negative of log likelihood value, so that the parameters can be optimized when minimize the cross-entropy error.
Does anyone have the same problem?
I read the paper "Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank" recently and was confused with the error function of RNTN parameters, that is equation (2) in part 4.4. As we know, the cross-entropy error should be the negative of log likelihood value, so that the parameters can be optimized when minimize the cross-entropy error.
Does anyone have the same problem?