Abstract: Systems and computer implemented methods for classifying documents are provided that include: pretraining and then fine tuning a machine learning model with a domain specific dataset that includes a plurality of documents each annotated with at one label selected from a plurality of predefined labels for a given domain; and predicting using the trained/fine tuned machine learning model, at least one label from the plurality of labels for at least one other document. The machine learning model is preferably fine tuned using a label attention multi-task learning process that includes: a first task for training the machine learning model with respect to all labels used for the plurality of documents in the dataset, and a second task for training the machine learning model with respect to a subset of all of the labels used for the plurality of documents in the dataset.