Abstract: A computer-implemented method is provided. The method may comprise: obtaining at least one document to be classified; classifying, using a machine learning model including an artificial neural network (ANN) and an attention mechanism, the at least one document into at least two classes; determining, for each of the at least one document, a confidence value of the classifying, based on one or more outputs of one or more nodes comprised in the ANN; assigning, to each of the at least one document, based at least in part on the confidence value, one of at least two categories that are associated with different degrees of credibility of the classifying; and providing for display one or more of the at least one document with: the assigned category and attention information that indicates significance of one or more parts of each document provided for display in the classifying of said document.

Abstract: A process for removing impurities from a crystallized metal sulfate, including contacting crystallized metal sulfate with a liquor rich in metal sulfate. The metal may be cobalt, nickel, or manganese, and the impurities may be magnesium or calcium. The liquor rich in metal sulfate may be an overflow liquor from crystallization of the metal sulfate, and said overflow liquor may be subject to one or more impurities removal steps prior to contacting the crystallized metal sulfate, such that the overflow liquor contains lower levels of impurities than the crystallized metal sulfate to be contacted. A counter-current wash circuit may be used to remove impurities from a crystallized metal sulfate, whereby a plurality of washing tanks are configured to receive crystallized metal sulfate in a sequence, and washing liquor in reverse of said sequence.

Abstract: A computer-implemented method is provided. The method may comprise: obtaining at least one document to be classified; classifying, using a machine learning model including an artificial neural network (ANN) and an attention mechanism, the at least one document into at least two classes; determining, for each of the at least one document, a confidence value of the classifying, based on one or more outputs of one or more nodes comprised in the ANN; assigning, to each of the at least one document, based at least in part on the confidence value, one of at least two categories that are associated with different degrees of credibility of the classifying; and providing for display one or more of the at least one document with: the assigned category and attention information that indicates significance of one or more parts of each document provided for display in the classifying of said document.