Efficient Selection Based on Integrated Information for Dialogue State Tracking

Hongyun Du, Jikun Dong, Shengyu Fan, Shengjie Jia, Feiyue Diao, Jiran Zhu, Wei Sun, Hui Yu, Weizhi Xu

Abstract: Dialogue State Tracking (DST) is a critical component in Task-Oriented Dialogue (TOD) systems, responsible for generating the dialogue state at each turn. Current approaches often struggle with complicated conversational contexts, primarily due to issues of information redundancy and insufficiency, which adversely affects accuracy. To address these challenges, we propose a novel approach termed Selection based on Integrated Information (SII). This method comprises three key components: an Information Integrator, which distills core information from the dialogue; an Information Selector, which identifies the most pertinent core information for each slot; and a State Predictor, which executes predictions based on the selected information. By focusing on selected information, SII demonstrates enhanced performance, achieving joint goal accuracies of 55.44% and 59.89% on the MultiWOZ2.0 and MultiWOZ2.1 datasets, respectively.