Connect with us

Social chatbots can provide information and create fluent dialogue. A recent study proposes a chatbot, which is capable not only to generate information-based chat but also to have its own opinions and personality.

When a user connects to the chatbot, Natural Language Processing Pipeline performs text extraction and classification. Then, a Dialogue Manager selects the best answer possible, referencing to the user-provided information if possible.

Emora An Inquisitive Social Chatbot Who Cares For You

Image credit: Sarah E. Finch / arXiv:2009.04617

The chatbot understands a lot of synonyms and idioms and can maintain a conversation on various topics. It can recommend movies or music based on the user’s interests, propose plans for traveling, or talk about relationships, school, and work. As an opinion-focused chatbot, it has its own opinion about movies and can talk about its own basketball playing style, for example. The user ratings confirmed that opinion-oriented conversation is better received than fact-based one.

Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI. The traditional approach of information-sharing topic handlers is balanced with a focus on opinion-oriented exchanges that Emora delivers, and new conversational abilities are developed that support dialogues that consist of a collaborative understanding and learning process of the partner’s life experiences. We present a curated dialogue system that leverages highly expressive natural language templates, powerful intent classification, and ontology resources to provide an engaging and interesting conversational experience to every user.