Abstract: A computer architecture for labeling documents is disclosed. According to some aspects, a computer accesses a collection of documents corresponding to a medical encounter and a labeling for the collection, wherein the labeling comprises one or more labels representing medical annotations assigned to the medical encounter. The computer computes, using a Hierarchical Attention Network (HAN), for each of a plurality of document-label pairs, a probability that a document of the document-label pair corresponds to a label of the document-label pair based on one or more features of text in the document, wherein each document-label pair comprises a document from the collection of documents and a label from the labeling. The computer provides an output representing the computed probabilities.