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.

arXiv comment18 pages, 5 figures, Alexa Prize Proceedings Paper (https://developer.amazon.com/alexaprize/proceedings), Alexa Prize University Competition to advance Conversational AI

References in corpus (7)

• A Neural Conversational Model
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• LSTM based Conversation Models
• Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
• 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 (50)

• Recipes for Safety in Open-domain Chatbots
• Low-Resource Knowledge-Grounded Dialogue Generation
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Zero-Resource Knowledge-Grounded Dialogue Generation
• Towards Ecologically Valid Research on Language User Interfaces
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
• 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
• Beyond Turing: Intelligent Agents Centered on the User
• A Re-classification of Information Seeking Tasks and Their Computational Solutions
• A Survey of Document Grounded Dialogue Systems (DGDS)
• Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
• Deploying Lifelong Open-Domain Dialogue Learning
• TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System
• Emora: An Inquisitive Social Chatbot Who Cares For You
• Do Fine-tuned Commonsense Language Models Really Generalize?
• DiscASP: A Graph-based ASP System for Finding Relevant Consistent Concepts with Applications to Conversational Socialbots
• Sounding Board: A User-Centric and Content-Driven Social Chatbot
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
• Detecting Offensive Content in Open-domain Conversations using Two Stage Semi-supervision
• Building Proactive Voice Assistants: When and How (not) to Interact
• Do We Need Online NLU Tools?
• 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
• User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant
• Implicit Discourse Relation Identification for Open-domain Dialogues
• Content Selection Network for Document-grounded Retrieval-based Chatbots
• Dompteur: Taming Audio Adversarial Examples
• Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
• Contextual Topic Modeling For Dialog Systems
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• Rating Prediction in Conversational Task Assistants with Behavioral and Conversational-Flow Features
• Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation
• Hybrid Code Networks using a convolutional neural network as an input layer achieves higher turn accuracy
• Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
• Would you Like to Talk about Sports Now? Towards Contextual Topic Suggestion for Open-Domain Conversational Agents
• Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
• A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis
• An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
• Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems
• Data-Efficient Methods for Dialogue Systems
• Building A User-Centric and Content-Driven Socialbot
• Target-Guided Open-Domain Conversation