Strategy of the Negative Sampling for Training Retrieval-Based Dialogue Systems
This work addresses the challenge of enhancing automated dialogue systems for customer service, but it appears incremental as it focuses on optimizing negative sampling within an existing framework.
The paper tackles the problem of improving retrieval-based dialogue systems for customer support by analyzing how the choice of negative samples affects quality, and it reports significant improvements when using negative responses from a transformed distribution.
The article describes the new approach for quality improvement of automated dialogue systems for customer support service. Analysis produced in the paper demonstrates the dependency of the quality of the retrieval-based dialogue system quality on the choice of negative responses. The proposed approach implies choosing the negative samples according to the distribution of responses in the train 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.