Strategy of the Negative Sampling for Training Retrieval-Based Dialogue Systems

The article describes the new approach for quality improvement of automated dialogue systems for customer support service. The analysis produced in the paper demonstrates the dependency of the quality of the retrieval-based dialogue system on the choice of negative responses required for training the system. The proposed approach implies choosing the negative samples according to the distribution of responses in the training set. In this implementation, the negative samples are randomly chosen from the original response distribution and from the “artificial” distribution of negative responses, such as uniform distribution or the distribution obtained by transformation of the original one. The results obtained for the implemented systems and reported in this paper confirm the significant improvement of automated dialogue systems quality in case of using the negative responses from transformed distribution.