I am dealing with a problem in which I have to label the inputs (in a sequence format) to 5 distinct classes. The input would be like:

X = {x_1,_x_2,...,X_500}

and the output should be something like:

Y = {Y_1,Y_2,...,Y_500}

But the problem is that too many of the labels are from the first class so a sample output would have many first class labels and only a few (5 or 6 samples) related to other classes.

The classifier tends to learn to classify everything to first class and yet get higher accuracy which is not correct.

What are your suggestions?

I am dealing with a problem in which I have to label the inputs (in a sequence format) to 5 distinct classes. The input would be like:

X = {x_1,_x_2,...,X_500}

and the output should be something like:

Y = {Y_1,Y_2,...,Y_500}

But the problem is that too many of the labels are from the first class so a sample output would have many first class labels and only a few (5 or 6 samples) related to other classes.

The classifier tends to learn to classify everything to first class and yet get higher accuracy which is not correct.

What are your suggestions?

Edit: Loss function being used is cross entropy loss, the architecture itself is a bilstm which is applied after an embedding layer, to be more precise:

InputLayer -> Embedding -> BidirectionalLSTM -> NN -> Softmax

The input is in character format (indexes of characters) and the output for each character is of 5 distinct classes while the problem is:

Most of characters belong to first class.

PS: I hope this would leave enough information.

I am dealing with problem in which i have to label the inputs (in a sequence format) to 5 distinct classes. The input would be like:

X = {x_1,_x_2,...,X_500}

and the output should be something like:

Y = {Y_1,Y_2,...,Y_500}

But the problem lies where too many of labels are from first class so a sample output would have many frist class labels and only a few (5 or 6 samples) related to other classes.

The classifier tends to learn to classify everything to first class and yet get higher accuracy which is not correct. What you propose?

I am dealing with a problem in which I have to label the inputs (in a sequence format) to 5 distinct classes. The input would be like:

X = {x_1,_x_2,...,X_500}

and the output should be something like:

Y = {Y_1,Y_2,...,Y_500}

But the problem is that too many of the labels are from the first class so a sample output would have many first class labels and only a few (5 or 6 samples) related to other classes.

The classifier tends to learn to classify everything to first class and yet get higher accuracy which is not correct.

What are your suggestions?