The goal of text-to-text generation is to make machines express like a human in many
applications such as conversation, summarization, and translation. It is one of the most …

Recommender systems are embracing conversational technologies to obtain user
preferences dynamically, and to overcome inherent limitations of their static models. A …

One of the hardest problems in the area of Natural Language Processing and Artificial
Intelligence is automatically generating language that is coherent and understandable to …

End-to-end neural dialogue generation has shown promising results recently, but it does not
employ knowledge to guide the generation and hence tends to generate short, general, and …

Beyond current conversational chatbots or task-oriented dialogue systems that have
attracted increasing attention, we move forward to develop a dialogue system for automatic …

In multi-turn dialogue generation, response is usually related with only a few contexts.
Therefore, an ideal model should be able to detect these relevant contexts and produce a …

Evaluation is crucial in the development process of task-oriented dialogue systems. As an
evaluation method, user simulation allows us to tackle issues such as scalability and cost …

The success of emotional conversation systems depends on sufficient perception and
appropriate expression of emotions. In a real-world conversation, we firstly instinctively …

Medical dialogue generation aims to provide automatic and accurate responses to assist
physicians to obtain diagnosis and treatment suggestions in an efficient manner. In medical …

Today's conversational agents often generate responses that not sufficiently informative.
One way of making them more informative is through the use of of external knowledge …