Class balancing for efficient active learning in imbalanced datasets

Recent developments in active learning algorithms for NLP tasks show promising results in terms of reducing labelling complexity. In this paper we extend this effort to imbalanced datasets; we bridge between the active learning approach of obtaining diverse and informative examples, and the heuristic of class balancing used in imbalanced datasets. We develop a novel tune-free weighting technique that can be applied to various existing active learning algorithms, adding a component of class balancing. We compare several active learning algorithms to their modified version on multiple public datasets and show that when the classes are imbalanced, with manual annotation effort remaining equal the modified version significantly outperforms the original both in terms of the test metric and the number of obtained minority examples. Moreover, when the imbalance is mild or non-existent (classes are completely balanced), our technique does not harm the base algorithms.