Going beyond FAQ assistants with machine learning and open source tools
Location: LL21 A/B
Who is this presentation for?Machine Learning Engineers, Data Scientist, Product Managers
AI assistants are one of the most in-demand topics in the tech industry right now. With technology moving forward and data becoming more available, companies strive to build their own conversational software. When built well, AI assistants provide great strategic business value and are fun to interact with. However, the majority of assistants built to this day are developed using just a set of rules or a state machine and don’t go beyond simple FAQ interactions. This doesn’t scale in production and often provides a rather disappointing user experience
In this workshop, you are going to take a different approach and build an intelligent assistant without any predefined rules. Instead, using open source libraries Rasa NLU and Rasa Core, you’ll build an assistant which learns by observing real conversations. At the end of this workshop, you will have built an engaging and fully functioning conversational assistant based entirely on machine learning. The workshop will consist of the following stages:
Stage 1: Natural language understanding. You will start with language understanding, bootstrapping from very little annotated training data. In this stage, you will also tackle the challenges of going beyond pretrained word vectors for NLU and enabling the assistant to capture more than one intention per user input.
Stage 2: Dialogue management. You will use machine learning to build the AI assistant’s ability to handle increasingly complex multi-turn dialogues based on the actual conversational data. You will also enable the assistant to actually complete user-requested tasks by connecting the assistant to external APIs and using the knowledge of the outside world to steer the conversation.
Stage 3: Closing the feedback loop. In the last section, you will close the feedback loop by improving the performance of the assistant by using the real-time user feedback and conversation history.
The attendees of this workshop will learn the fundamentals of building conversational AI, the foundations of machine learning models behind the NLU and dialogue management, the best practices of preparing training data and developing intelligent AI assistants that scale in production.
Prerequisite knowledgeTo get the most of the workshop, the attendees should have a working knowledge of programming in Python and an understanding of the fundamental ML concepts.
Materials or downloads needed in advance
What you'll learnThe main ideas and skills the attendees will learn: - Machine learning behind the NLU and dialogue management - Techniques of building language agnostic NLU models - Best practices of gathering and preparing the training data - Best practices of closing the feedback loop using real-time user feedback and conversation history - Implementing conversational assistants from scratch using open source tools Rasa NLU and Rasa Core
Justina has a background in Econometrics and Data Analytics. Her curiosity for Data Science and human behaviour analytics has taken her to many places and industries – over the past three years she has been doing Data Science work across video gaming, fintech, insurance industries. Her interest in chatbots, natural language processing and open source has led her to Rasa, a Berlin-based conversational AI startup where she works as a Developer Advocate focusing on improving developer experience in using open source software for conversational AI.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of O'Reilly AI contacts