Figure 4.
The many-to-one prediction task for the LSTM, in which a document representation is fed in at eachtimestep, and it makes a prediction (e.g. diagnosis) at the end of the sequence.
The many-to-one prediction task for the LSTM, in which a document representation is fed in at eachtimestep, and it makes a prediction (e.g. diagnosis) at the end of the sequence.