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 …

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 …

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 policy plays an important role in task-oriented spoken dialogue systems. It
determines how to respond to users. The recently proposed deep reinforcement learning …

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 …

Recently, deep reinforcement learning (DRL) has been used for dialogue policy
optimization. However, many DRL-based policies are not sample-efficient. Most recent …

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 …

In order to improve the sample-efficiency of deep reinforcement learning (DRL), we
implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS) …

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 …

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 …