Despite myriad efforts in the literature designing neural dialogue generation systems in
recent years, very few consider putting restrictions on the response itself. They learn from …

In conversation, a general response (eg,“I don't know”) could correspond to a large variety of
input utterances. Previous generative conversational models usually employ a single model …

Current neural network-based conversational models lack diversity and generate boring
responses to open-ended utterances. Priors such as persona, emotion, or topic provide …

Encoder-decoder based neural architectures serve as the basis of state-of-the-art
approaches in end-to-end open domain dialog systems. Since most of such systems are …

Facing the COVID-19 pandemic, governments have implemented a wide range of policies to
contain the spread of the virus. During the pandemic, large amounts of COVID-19-related …

Conversational agent quality is currently assessed using human evaluation, and often
requires an exorbitant number of comparisons to achieve statistical significance. In this …

Although chatbots have been very popular in recent years, they still have some serious
weaknesses which limit the scope of their applications. One major weakness is that they …

Abstract Natural Language Generation (NLG) has received much attention with rapidly
developing models and ever-more available data. As a result, a growing amount of work …

Dialogue generation models face the challenge of producing generic and repetitive
responses. Unlike previous augmentation methods that mostly focus on token manipulation …

Being able to reply with a related, fluent, and informative response is an indispensable
requirement for building high-quality conversational agents. In order to generate better …