Recent advances and challenges in task-oriented dialog systems
Due to the significance and value in human-computer interaction and natural language
processing, task-oriented dialog systems are attracting more and more attention in both …
processing, task-oriented dialog systems are attracting more and more attention in both …
The price of debiasing automatic metrics in natural language evaluation
For evaluating generation systems, automatic metrics such as BLEU cost nothing to run but
have been shown to correlate poorly with human judgment, leading to systematic bias …
have been shown to correlate poorly with human judgment, leading to systematic bias …
Neural user simulation for corpus-based policy optimisation for spoken dialogue systems
User Simulators are one of the major tools that enable offline training of task-oriented
dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The …
dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The …
AgentGraph: Toward universal dialogue management with structured deep reinforcement learning
Dialogue policy plays an important role in task-oriented spoken dialogue systems. It
determines how to respond to users. The recently proposed deep reinforcement learning …
determines how to respond to users. The recently proposed deep reinforcement learning …
Budgeted policy learning for task-oriented dialogue systems
This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a
Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions …
Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions …
Structured dialogue policy with graph neural networks
Recently, deep reinforcement learning (DRL) has been used for dialogue policy
optimization. However, many DRL-based policies are not sample-efficient. Most recent …
optimization. However, many DRL-based policies are not sample-efficient. Most recent …
Policy adaptation for deep reinforcement learning-based dialogue management
Policy optimization is the core part of statistical dialogue management. Deep reinforcement
learning has been successfully used for dialogue policy optimization for a static pre-defined …
learning has been successfully used for dialogue policy optimization for a static pre-defined …
Actor-double-critic: Incorporating model-based critic for task-oriented dialogue systems
In order to improve the sample-efficiency of deep reinforcement learning (DRL), we
implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS) …
implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS) …
A teacher-student framework for maintainable dialog manager
Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems.
However, extending RL-based systems to handle new intents and slots requires a system …
However, extending RL-based systems to handle new intents and slots requires a system …
Deep reinforcement learning for on-line dialogue state tracking
Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast
as a supervised training problem, which is not convenient for on-line optimization. In this …
as a supervised training problem, which is not convenient for on-line optimization. In this …