To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL
with up to 11 billion parameters, trained on both Chinese and English social media …

Most prior work in dialogue modeling has been on written conversations mostly because of
existing data sets. However, written dialogues are not sufficient to fully capture the nature of …

Retrieval-enhanced text generation has shown remarkable progress on knowledge-
intensive language tasks, such as open-domain question answering and knowledge …

Knowledge-grounded conversation has led to great progress in producing informative
dialog responses by leveraging external knowledge. This work focuses on two affiliated …

For a task-oriented dialogue system to provide appropriate answers to and services for
users' questions, it is necessary for it to be able to utilize knowledge related to the topic of …

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This
edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct …

As knowledge-grounded dialogue systems are attracting intense research interest,
technology that facilitates reference to various types of external knowledge as dialogue …

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-
scale and high-quality annotated conversations. Furthermore, most of the publicly available …

Existing studies in conversational AI mostly treat task-oriented dialog (TOD) and question
answering (QA) as separate tasks. Towards the goal of constructing a conversational agent …

Featured Application Core technology for document-grounded conversation. Abstract
Document-grounded conversation (DGC) is a natural language generation task to generate …