Going beyond FAQ assistants with machine learning and open source tools

Description

AI assistants are one of the most in-demand topics in the tech industry right now. With technology moving forward and more data becoming 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 today 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.

Justina Petraityte takes a different approach and details how to build an intelligent assistant without any predefined rules. Instead, using open source libraries Rasa NLU and Rasa Core, you’ll build an assistant that learns by observing real conversations. You’ll leave with an engaging and fully functioning conversational assistant based entirely on machine learning.

Outline:

Stage 1: Natural language understanding (NLU)—You start with language understanding and bootstrapping from very little annotated training data. In this stage, you’ll 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’ll use machine learning to build the AI assistant’s ability to handle increasingly complex multiturn dialogues based on the actual conversational data. You’ll 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—You’ll close the feedback loop by improving the performance of the assistant by using the real-time user feedback and conversation history.