pydial相关论文初步整理

semi用户话语解析部分：

1.基于知识共享的大规模多域信念跟踪 Large-scale Multi-Domain Belief Tracking with Knowledge Sharing(2018)

2.联合学习特色提取器的封建对话管理Feudal Dialogue Management with Jointly Learned Feature Extractors(2018)

3.处理对象及其关系:对话实体对话模型: Addressing Objects and Their Relations: The Conversational Entity (2018)

4.神经信念跟踪:数据驱动的对话状态跟踪:Neural Belief Tracker: Data-Driven Dialogue State Tracking(2017)

5.使用简单的特定于语言的规则微调单词向量空间: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules(2017)

6.使用单语和跨语言约束对分布词向量空间进行语义专门化Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints(2017)

7.潜在意图对话模式分析:Latent Intention Dialogue Models(2017)

policy对话政策部分：

1.基于语料库的口语对话系统优化策略的神经用户模拟 Neural User Simulation for Corpus-based Policy Optimisation of Spoken Dialogue Systems (2018)

2.基于深度强化学习的不确定度基准估计用于对话政策优化:Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation(2018)

3.多领域的强化学习:“Feudal Reinforcement Learning for Dialogue Management in Large Domains(2018)

4.基于强化学习的面向任务的对话管理:A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management(2017)

5.基于神经网络的对话策略优化的不确定性估计:Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation(2017)

6.高效的采样和有监督的强化学习的对话管理:Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management(2017)

7.对话管理的子领域建模与分层强化学习:Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning(2017)

8.对话策略学习领域及用户满意度奖励评估:Domain-independent User Satisfaction Reward Estimation for Dialogue Policy Learning(2017)

9.对话管理器领域中使用高斯过程强化学习:Dialogue manager domain adaptation using Gaussian process reinforcement learning(2017)

semo对话生成部分：

1.口语对话系统的变域跨域自然语言生成 Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems(2018)

未分类:

1.基于网络的端到端可训练的面向任务的对话系统：A Network-based End-to-End Trainable Task-oriented Dialogue System(2017)