Machine learning is an integral part of the future of search but it’s important to understand what that really means.
AI is misconstrued as a magic bullet that can be added to any system and everything suddenly works better. But it’s more complicated than that.
The conceptual architecture of future search is highly modular. One that relates to an application or set of applications that can do a lot of different, distinct things. It has some sort of description of this functionality and how it fits together, like a domain or a world model.
Classical search functionality exists within that specification. These modules individually aren’t so revolutionary, not requiring much intelligence so far. Just a lot of specification. In fact, this is just what would have once been called an expert system.
How does Machine Learning fit in? There is no such thing as general-purpose ML (yet). Instead, ML algorithms are specific solutions to specific classes of problems.
In future search, ML configures the system in real time. It decides which modules are activated for a given request by deducing goals. The primary means for this is natural language processing executed on input, but also includes other methods like data sources, patterns of behaviour, or biometrics.