Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …

Abstract Virtual Customer Assistants (VCAs) are revolutionizing the way users interact with
machines. VCAs allow a far more natural interaction, and are gaining an increasingly large …

Nowadays, open-domain dialogue models can generate acceptable responses according to
the historical context based on the large-scale pre-trained language models. However, they …

Reinforcement learning (RL) has been widely used in text generation to alleviate the
exposure bias issue or to utilize non-parallel datasets. The reward function plays an …

Pre-trained language models (PrLMs) have demonstrated superior performance due to their
strong ability to learn universal language representations from self-supervised pre-training …

In knowledge-grounded dialogue generation, pre-trained language models (PLMs) can be
expected to deepen the fusing of dialogue context and knowledge because of their superior …

Leveraging task-aware annotated data as supervised signals to assist with self-supervised
learning on large-scale unlabeled data has become a new trend in pre-training language …

Open-domain dialogue systems aim to interact with humans through natural language texts
in an open-ended fashion. Despite the recent success of super large dialogue systems such …

The recent spread of Deep Learning-based solutions for Artificial Intelligence and the
development of Large Language Models has pushed forwards significantly the Natural …

Each utterance in multi-turn empathetic dialogues has features such as emotion, keywords,
and utterance-level meaning. Feature transitions between utterances occur naturally …