Partially observable Markov decision processes for spoken dialog systems

By Jason Williams, Susannah Young. 2007

967 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.

In Artificial Intelligence

Citations in the corpus

Lifelong and Continual Learning Dialogue Systems: Learning during Conversation (2021, background): “(2) Task-oriented chatbots (Williams and Young 2007; Wen et al. 2017) designed to assist users to complete tasks based on users’ requests, e.”
Deal or No Deal? End-to-End Learning of Negotiation Dialogues (2017, background): “Most work on goal orientated dialogue systems has assumed that state representations are annotated in the training data (Williams and Young, 2007; Henderson et al., 2014; Wen et al., 2016).”
Policy Networks with Two-Stage Training for Dialogue Systems (2016, methodology): “Within the POMDP framework, the state at time t , S t , is not directly observable.”
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems (2018, background): “Discussions: Conventional task-oriented dialog systems (Williams and Young, 2007), which are still widely used in commercial systems, require a multitude of human efforts in system designing”
End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning (2016, background): “…cuisine type and price range to use as search criteria for a restaurant, and the dialog history such as whether a slot has already been asked for or conﬁrmed, whether a restaurant has been offered already, or whether a user has a favorite cui-sine listed in their proﬁle (Williams and Young, 2007).”
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems (2016, methodology): “2016) and RL for learning dialogue policies (Levin, Pieraccini, and Eckert 2000; Singh et al. 2000; Williams and Young 2007; Gašić et al. 2010; Fatemi et al. 2016).”
Crowd-sourcing NLG Data: Pictures Elicit Better Data. (2016, background): “The data will be released as part of this submission.”
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management (2017, background): “More recently, it has been formulated as a planning problem and solved using reinforcement learning (RL) to optimise a dialogue policy through interaction with users (Levin and Pieraccini, 1997; Roy et al., 2000; Williams and Young, 2007; Jurčı́ček et al., 2011).”
From Eliza to XiaoIce: challenges and opportunities with social chatbots (2018, background): “The DM also includes dialog state tracking and policy selection, so that the dialog agent can make more robust decisions (Williams and Young, 2007).”
Global-to-local Memory Pointer Networks for Task-Oriented Dialogue (2019, background): “For the modularized systems (Williams & Young, 2007; Wen et al., 2017), a set of modules for natural language understanding (Young et al., 2013; Chen et al., 2016), dialogue state tracking (Lee & Stent, 2016; Zhong et al., 2018), dialogue management (Su et al., 2016), and natural language…”
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning (2017, background): “The first decomposes a dialog system into a pipeline, typically including language understanding, dialog state tracking, action selection policy, and language generation (Levin et al., 2000; Singh et al., 2002; Williams and Young, 2007; Williams, 2008; Hori et al., 2009; Lee et al., 2009; Griol et a”
End-to-end optimization of goal-driven and visually grounded dialogue systems (2017, methodology): “In addition, successful applications of the RL framework to dialogue often rely on a predeﬁned structure of the task, such as slot-ﬁlling tasks [ Williams and Young, 2007 ] where the task can be casted as ﬁlling in a form.”
Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning (2016, background): “Reinforcement Learning (RL): RL has been a popular approach for learning the optimal dialog policy of a task-oriented dialog system (Singh et al., 2002; Williams and Young, 2007; Georgila and Traum, 2011; Lee and Eskenazi, 2012).”
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems (2019, background): “Dialogue State Tracking Traditional dialogue state tracking models combine semantics extracted by language understanding modules to estimate the current dialogue states (Williams and Young, 2007; Thomson and Young, 2010; Wang and Lemon, 2013; Williams, 2014), or to jointly learn speech understanding”
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset (2019, background): “However, it is doubtful that new data-driven systems built with this type of corpus would show much improvement since they would be biased by the existing system and likely mimic its limitations (Williams and Young, 2007).”