To handle these phenomena, we suggest a Dialogue State Tracking with Slot Connections (DST-SC) model to explicitly consider slot correlations throughout totally different domains. Specially, we first apply a Slot Attention to be taught a set of slot-specific features from the original dialogue and then integrate them using a slot info sharing module. Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking Yexiang Wang writer Yi Guo creator Siqi Zhu writer 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). In this paper, we propose a brand new architecture to cleverly exploit ontology, which consists of Slot Attention (SA) and Value Normalization (VN), known as SAVN. SAS: Dialogue State Tracking by way of Slot Attention and Slot Information Sharing Jiaying Hu creator Yan Yang writer Chencai Chen author Liang He writer Zhou Yu writer 2020-jul textual content Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics Online conference publication Dialogue state tracker is liable for inferring consumer intentions through dialogue history. We suggest a Dialogue State Tracker with Slot Attention and Slot Information Sharing (SAS) to cut back redundant information’s interference and improve lengthy dialogue context tracking.
