|
To handle these phenomena, we suggest a Dialogue State Tracking with Slot Connections (DST-SC) mannequin to explicitly consider slot correlations across different domains. Specially, we first apply a Slot Attention to study a set of slot-particular options from the original dialogue after which integrate them utilizing a slot info sharing module. Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking Yexiang Wang author Yi Guo writer 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 problems of dialogue state tracking (DST). On this paper, we suggest a new architecture 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 writer Chencai Chen writer Liang He writer Zhou Yu writer 2020-jul text Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics Online convention publication Dialogue state tracker is accountable for inferring user intentions through dialogue history. We propose a Dialogue State Tracker with Slot Attention and Slot Information Sharing (SAS) to reduce redundant information’s interference and improve long dialogue context tracking. |
|