Incorporating the Structure of the Belief State in End-to-End Task-Oriented Dialogue Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Simple Language Model for Task-Oriented Dialogue (2020, methodology): “[45] incorporated dialogue state tracking and jointly trained with response generation using a sequence-to-sequence approach.”
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems (2020, unknown): “…Madotto et al., 2020a; Neelakantan et al., 2019; Qin et al., 2019, 2020; Raghu et al., 2019; Haihong et al., 2019; He et al., 2020) and hybrid (Shu et al., 2018; Lei et al., 2018; Zhang et al., 2019a; Mehri et al., 2019; Chen et al., 2019; Peng et al., 2020a; Ham et al., 2020; Hosseini-Asl…”
MOSS: End-to-End Dialog System Framework with Modular Supervision (2019, background): “Shu et al. (2018) extended TSCP (Lei et al. 2018) by separately decoding information slot and predicting requested slot for dialog state tracking.”