Structured Dialogue Policy with Graph Neural Networks

By Lu Chen, Bowen Tan, Sishan Long, Kai Yu. 2018

33 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, methodology): “In the realm of domain adaptation, works assume a fixed number of actions that are slot-independent, and focus on the inclusion of slot-dependent actions when the domain changes (Wang et al., 2015; Casanueva et al., 2018; Chen et al., 2018; Chen et al., 2020; Lin et al., 2021).”
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management (2020, methodology): “Instead, the relationships among all the sub-agents can be represented by a graph [8], where each node of the graph denotes a corresponding sub-agent, and the directed edge between two sub-agents means that the starting sub-agent will send some information (or message) to the ending sub-agent, as sh”
Semantic Parsing with Dual Learning (2019, methodology): “Yin and Neubig (2017) and Chen et al. (2018a) both transform the generation of logical forms into query graph construction.”
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks (2020, background): “Many GNN variants are proposed and also applied in various NLP tasks, such as text classiﬁcation (Yao, Mao, and Luo 2019), machine translation (Marcheg-giani, Bastings, and Titov 2018), dialogue policy optimization (Chen et al. 2018b; 2019; 2018a) etc.”
DynaEval: Unifying Turn and Dialogue Level Evaluation (2021, methodology): “Chen et al. (2018) modeled structured dialogue policy with GNN and (Qin et al., 2020) proposes a joint framework leveraging graph attention network (Veliˇckovi´c et al., 2018) for both dialogue act recognition and sentiment classiﬁcation.”
Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning (2022, methodology): “In the realm of domain adaptation, works assume a ﬁxed number of actions that are slot-independent, and focus on the inclusion of slot-dependent actions when the domain changes (Wang et al., 2015; Casanueva et al., 2018; Chen et al., 2018; Chen et al., 2020; Lin et al., 2021).”
Neural Approaches to Conversational AI (2018, unknown): “rent networks (Zhao and Eskenazi,´ 2016; Williams et al., 2017) that can more easily capture information from conversational histories than expert-designed dialogue states. In another recent example, Chen et al. (2018) used graph neural networks to model the Q-function, with nodes in the graph corre”