What You Must Know to Build AI Systems That Understand Natural Language

New AI solutions in question answering, chatbots, structured data extraction, text generation, and inference all require deep understanding of the nuances of human language. David Talby shares challenges, risks, and best practices for building NLU-based systems, drawing on examples and case studies from products and services built by Fortune 500 companies and startups over the past six years. David also highlights some of the differences between language understanding and other machine learning and deep learning applications. Topics include: - What gave natural language understanding its reputation as an “AI complete” problem - The many languages we speak every day and the resulting need to train domain-specific NLP models for most systems - The evolution from “traditional” machine learning and information retrieval techniques to current state-of-the-art systems, covering both the “simple” parts of common NLP Q&A or bot solutions and where “advanced” AI fits in - Guidelines to architecting a system that trains and serves large, current, accurate domain-specific NLP models using open source software David Talby is a chief technology officer at Pacific AI, helping fast-growing companies apply big data and data science techniques to solve real-world problems in healthcare, life science, and related fields. David has extensive experience in building and operating web-scale data science and business platforms, as well as building world-class, Agile, distributed teams. Previously, he was with Microsoft’s Bing Group, where he led business operations for Bing Shopping in the US and Europe, and worked at Amazon both in Seattle and the UK, where he built and ran distributed teams that helped scale Amazon’s financial systems. David holds a PhD in computer science and master’s degrees in both computer science and business administration.