To handle these phenomena, we propose a Dialogue State Tracking with Slot Connections (DST-SC) model to explicitly consider slot correlations throughout different domains. Specially, we first apply a Slot Attention to study a set of slot-specific features from the original dialogue and then integrate them utilizing a slot information sharing module. Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking Yexiang Wang creator Yi Guo writer Siqi Zhu creator 2020-nov text Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) Association for Computational Linguistics Online convention publication Incompleteness of domain ontology and unavailability of some values are two inevitable issues of dialogue state tracking (DST). On this paper, we suggest a brand new structure to cleverly exploit ontology, which consists of Slot Attention (SA) and Value Normalization (VN), known as SAVN. SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing Jiaying Hu creator Yan Yang author Chencai Chen author Liang He author Zhou Yu creator 2020-jul text Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics Online conference publication Dialogue state tracker is chargeable for inferring person intentions by means of dialogue history. We suggest a Dialogue State Tracker with Slot Attention and Slot Information Sharing (SAS) to reduce redundant information’s interference and improve lengthy dialogue context monitoring.
