Conversational AI: The Science Behind the Alexa Prize

Abstract

Conversational agents are exploding in popularity. However, much work remains in the area of social conversation as well as free-form conversation over a broad range of domains and topics. To advance the state of the art in conversational AI, Amazon launched the Alexa Prize, a 2.5-million-dollar university competition where sixteen selected university teams were challenged to build conversational agents, known as socialbots, to converse coherently and engagingly with humans on popular topics such as Sports, Politics, Entertainment, Fashion and Technology for 20 minutes. The Alexa Prize offers the academic community a unique opportunity to perform research with a live system used by millions of users. The competition provided university teams with real user conversational data at scale, along with the user-provided ratings and feedback augmented with annotations by the Alexa team. This enabled teams to effectively iterate and make improvements throughout the competition while being evaluated in real-time through live user interactions. To build their socialbots, university teams combined state-of-the-art techniques with novel strategies in the areas of Natural Language Understanding, Context Modeling, Dialog Management, Response Generation, and Knowledge Acquisition. To support the efforts of participating teams, the Alexa Prize team made significant scientific and engineering investments to build and improve Conversational Speech Recognition, Topic Tracking, Dialog Evaluation, Voice User Experience, and tools for traffic management and scalability. This paper outlines the advances created by the university teams as well as the Alexa Prize team to achieve the common goal of solving the problem of Conversational AI.

18 pages, 5 figures, Alexa Prize Proceedings Paper (https://developer.amazon.com/alexaprize/proceedings), Alexa Prize University Competition to advance Conversational AI

References in corpus (4)

• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Slugbot: An Application of a Novel and Scalable Open Domain Socialbot Framework
• Predicting Causes of Reformulation in Intelligent Assistants

Cited by in corpus (34)

• Low-Resource Knowledge-Grounded Dialogue Generation
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• Towards Ecologically Valid Research on Language User Interfaces
• Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
• Alquist 2.0: Alexa Prize Socialbot Based on Sub-Dialogue Models
• Walert: Putting Conversational Search Knowledge into Action by Building and Evaluating a Large Language Model-Powered Chatbot
• A Survey of Document Grounded Dialogue Systems (DGDS)
• Beyond Turing: Intelligent Agents Centered on the User
• Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
• Deploying Lifelong Open-Domain Dialogue Learning
• Do Fine-tuned Commonsense Language Models Really Generalize?
• Emora: An Inquisitive Social Chatbot Who Cares For You
• DiscASP: A Graph-based ASP System for Finding Relevant Consistent Concepts with Applications to Conversational Socialbots
• TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
• Building Proactive Voice Assistants: When and How (not) to Interact
• ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
• Athena: Constructing Dialogues Dynamically with Discourse Constraints
• Two-pass Endpoint Detection for Speech Recognition
• ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents
• Content Selection Network for Document-grounded Retrieval-based Chatbots
• User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant
• Implicit Discourse Relation Identification for Open-domain Dialogues
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• Rating Prediction in Conversational Task Assistants with Behavioral and Conversational-Flow Features
• Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
• A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis
• Building A User-Centric and Content-Driven Socialbot
• Would you Like to Talk about Sports Now? Towards Contextual Topic Suggestion for Open-Domain Conversational Agents
• Target-Guided Open-Domain Conversation
• Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
• An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
• Data-Efficient Methods for Dialogue Systems