A case study on the importance of belief state representation for dialogue policy managementA case study on the importance of belief state representation for dialogue policy management Πλήρης Δημοσίευση σε Συνέδριο Conference Full Paper 2019-10-212018enA key component of task-oriented dialogue systems is the belief state representation, since it directly affects the policy learning efficiency. In this paper, we propose a novel, binary, compact, yet scalable belief state representation. We compare the standard verbose belief state representation (268 dimensions) with the domain-independent representation (57 dimensions) and the proposed representation (13 or 4 dimensions). To test those representations, the recently introduced Advantage Actor Critic (A2C) algorithm is exploited. The latter has not been tested before for any representation apart from the verbose one. We study the effect of the belief state representation within A2C under 0%, 15%, 30%, and 45% semantic error rate and conclude that the novel binary representation in general outperforms both the domain-independent and the verbose belief state representation. Further, the robustness of the binary representation is tested under more realistic scenarios with mismatched semantic error rates, within the A2C and DQN algorithms. The results indicate that the proposed compact, binary representation performs better or similarly to the other representations, being an efficient and promising alternative to the full belief.http://creativecommons.org/licenses/by/4.0/986-99019th Annual Conference of the International Speech CommunicationProceedings of the Annual Conference of the International Speech Communication Association Kotti Margarita Diakoloukas Vasileios Διακολουκας Βασιλeioς Papangelis Alexandros Lagoudakis Michail Λαγουδακης Μιχαηλ Stylianou, Yannis International Speech Communication Association Belief state Binary belief state representation Dialogue systems Domain-independent parametrisation