While communicating with a user, a task-oriented dialogue system has to track the user's
needs at each turn according to the conversation history. This process called dialogue state …

Task-oriented dialogue is often decomposed into three tasks: understanding user input,
deciding actions, and generating a response. While such decomposition might suggest a …

Pre-trained language models have been recently shown to benefit task-oriented dialogue
(TOD) systems. Despite their success, existing methods often formulate this task as a …

Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero
and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we …

We present a new method, Soloist, that uses transfer learning and machine teaching to build
task bots at scale. We parameterize classical modular task-oriented dialog systems using a …

Task-oriented dialogue (TOD) models have made significant progress in recent years.
However, previous studies primarily focus on datasets written by annotators, which has …

The MultiWOZ 2.0 dataset has greatly stimulated the research of task-oriented dialogue
systems. However, its state annotations contain substantial noise, which hinders a proper …

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented
dialogue in unseen domains without the expense of collecting in-domain data. In this paper …

Recently, pre-training methods have shown remarkable success in task-oriented dialog
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …

Task-oriented conversational systems often use dialogue state tracking to represent the
user's intentions, which involves filling in values of pre-defined slots. Many approaches have …