Pre-training models have been proved effective for a wide range of natural language
processing tasks. Inspired by this, we propose a novel dialogue generation pre-training …

To build a high-quality open-domain chatbot, we introduce the effective training process of
PLATO-2 via curriculum learning. There are two stages involved in the learning process. In …

Previous neural models on open-domain conversation generation have no effective
mechanisms to manage chatting topics, and tend to produce less coherent dialogs. Inspired …

To address the challenge of policy learning in open-domain multi-turn conversation, we
propose to represent prior information about dialog transitions as a graph and learn a graph …

Learning discrete dialog structure graph from human-human dialogs yields basic insights
into the structure of conversation, and also provides background knowledge to facilitate …

Human dialogue contains evolving concepts, and speakers naturally associate multiple
concepts to compose a response. However, current dialogue models with the seq2seq …

Article comment generation is a new and challenging task in natural language processing,
which has recently received much attention from researchers. In the article comment …

Although the Conditional Variational AutoEncoder (CVAE) model can generate more
diversified responses than the traditional Seq2Seq model, the responses often have low …

Response diversity has become an important criterion for evaluating the quality of open-
domain dialogue generation models. However, current evaluation metrics for response …

Towards human-like dialogue systems, current emotional dialogue approaches jointly
model emotion and semantics with a unified neural network. This strategy tends to generate …