liveBook · Manning

Pattern matching

As explained in Machines that Think

Pattern matching is the identification or reproduction of regularities in data without necessarily representing their underlying meaning.

Pattern matching reproduces regularities in data without necessarily representing what they mean. In language systems, scripted rules can produce replies that seem responsive, even when the system has no model of the situations being discussed. section 1.5.1

This approach works within familiar patterns but falters when inputs fall outside them. Translation illustrates the limitation: matching surface forms cannot reliably resolve whether “bank” refers to money or a riverbank without context. section 2.2.2

Figure 2.1 Example interaction with ELIZA. The system produces plausible responses when user input matches expected conversational patterns, but its behavior is driven by scripted rules combining keywords, pattern matching, and response templates rather than an understanding of meaning. As the dialogue progresses, this limitation becomes visible when responses no longer align with the user’s intent.

The ELIZA interaction shows how scripted patterns can produce plausible replies, then lose alignment with a user’s intent. section 2.2.2

How Machines that Think covers it

How deep it goes
Defines pattern matching through scripted language behavior and contrasts it with contextual interpretation, without detailing implementation.
Examples
Uses ELIZA’s scripted replies and the ambiguous word “bank” in translation to illustrate surface matching’s limits.
What you can do after
Evaluate fluent responses as evidence of surface pattern reproduction rather than proof of contextual understanding.
How it connects
Links pattern matching to syntax, prediction, response templates, context, and language understanding.

Also explained in

Compare how 16 books explain pattern matching →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Machines that Think. The section links point to the parts of the book it draws on.