Rasa: Open Source Language Understanding and Dialogue Management

Abstract

We introduce a pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software. Their purpose is to make machine-learning based dialogue management and language understanding accessible to non-specialist software developers. In terms of design philosophy, we aim for ease of use, and bootstrapping from minimal (or no) initial training data. Both packages are extensively documented and ship with a comprehensive suite of tests. The code is available at https://github.com/RasaHQ/

Presented at NIPS Workshop on Conversational AI, Code at https://github.com/RasaHQ

References in corpus (2)

• Scikit-learn: Machine Learning in Python
• A Network-based End-to-End Trainable Task-oriented Dialogue System

Cited by in corpus (29)

• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• Few-Shot Generalization Across Dialogue Tasks
• A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces
• Recent Advances and Challenges in Task-oriented Dialog System
• Robust Conversational AI with Grounded Text Generation
• ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
• Plato Dialogue System: A Flexible Conversational AI Research Platform
• Incrementalizing RASA's Open-Source Natural Language Understanding Pipeline
• Exploring Context-Aware Conversational Agents in Software Development
• A Financial Service Chatbot based on Deep Bidirectional Transformers
• Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems
• COVID-19 Smart Chatbot Prototype for Patient Monitoring
• Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges
• Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
• Multipurpose Intelligent Process Automation via Conversational Assistant
• A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining
• Modeling Intent, Dialog Policies and Response Adaptation for Goal-Oriented Interactions
• ConveRT for FAQ Answering
• AutoNLU: An On-demand Cloud-based Natural Language Understanding System for Enterprises
• A question-answering system for aircraft pilots' documentation
• Evaluating Variable-Length Multiple-Option Lists in Chatbots and Mobile Search
• Virtual Experience to Real World Application: Sidewalk Obstacle Avoidance Using Reinforcement Learning for Visually Impaired
• SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering
• Water quality information dissemination at real-time in South Africa using language modelling
• Improved Goal Oriented Dialogue via Utterance Generation and Look Ahead