Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding

Abstract

This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon's virtual assistant, Alexa. At Amazon, the infrastructure powers over 25,000 skills deployed through the ASK, as well as AWS's Amazon Lex SLU Service. The ASK emphasizes flexibility, predictability and a rapid iteration cycle for third party developers. It imposes inductive biases that allow it to learn robust SLU models from extremely small and sparse datasets and, in doing so, removes significant barriers to entry for software developers and dialogue systems researchers.

Published at the 1st Workshop on Conversational AI at NIPS 2017 (NIPS-WCAI)

References in corpus (5)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Frustratingly Easy Domain Adaptation
• A Deep Reinforcement Learning Chatbot
• Transfer Learning for Neural Semantic Parsing

Cited by in corpus (27)

• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• Conversational AI: The Science Behind the Alexa Prize
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Understanding and Mitigating the Security Risks of Voice-Controlled Third-Party Skills on Amazon Alexa and Google Home
• Contextual Slot Carryover for Disparate Schemas
• Learning Robust Dialog Policies in Noisy Environments
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery
• Neural Machine Translation For Paraphrase Generation
• Gunrock: A Social Bot for Complex and Engaging Long Conversations
• Scaling Multi-Domain Dialogue State Tracking via Query Reformulation
• Domain-Independent turn-level Dialogue Quality Evaluation via User Satisfaction Estimation
• Sounding Board: A User-Centric and Content-Driven Social Chatbot
• Statistical Model Compression for Small-Footprint Natural Language Understanding
• Style Attuned Pre-training and Parameter Efficient Fine-tuning for Spoken Language Understanding
• Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates
• Towards Personalized Dialog Policies for Conversational Skill Discovery
• Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding
• Efficient Large-Scale Domain Classification with Personalized Attention
• Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition
• Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification
• Towards Continual Entity Learning in Language Models for Conversational Agents
• Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding
• Meta learning to classify intent and slot labels with noisy few shot examples
• Delexicalized Paraphrase Generation
• Building A User-Centric and Content-Driven Socialbot
• Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding