The current crop of bots platforms (places that define bots to performs tasks) cannot help companies build AWESOME Chatbots because they are all based on machine learning (ML), writes AI programming guru Bruce Wilcox in Medium.
In contrast, Kore.ai has one that “combines ML and ChatScript to support Enterprise bots (serious customers like major banks with millions of users)”.
On its own ML is not be a complete natural language solution as it requires too much of training data – roughly 100 training sentences per intent, per his estimates.
And large volume ML training data is beyond most developers.
ChatScript, an open source rule-based scripting system, takes another approach for natural language. While ML and ChatScript both ultimately do the same thing (they use patterns to classify user inputs), there’s a difference. With ChatScript the human developer requires no external training samples to build a bot. Instead, the developer uses his understanding of language to figure out what the pattern should be, and can write extremely sophisticated patterns concisely.
In Bruce’s words, if ChatScript represents the 1st Wave AI (hand-crafted systems), ML represents 2nd Wave AI (machine learning where humans are required to label all sample inputs).
He pitches for 3rd Wave systems that integrate features of the first two waves and go beyond that, learning on their own and in the moment.
Because “most serious ChatScript developers use both”. Like Kore.ai.