Work In Progress
Pattern Matching
Why It Is Needed
People think about the world in terms of abstract concepts because it substantially simplifies interactions with the real world. What this means is that me map real world onto our world model by simplifying and aggregating incoming signals from the sensory organs. This process of simplification is called pattern matching because the agent is looking for abstract concepts in the raw signals, trying to find known patterns in the data. If we didn’t have pattern matching, then we would need to work with the raw data instead of its simplified representation, which is a lot more resource-intensive.
Ambiguity
The biggest challenge of pattern matching is ambiguity. Text is simpler to work with, so let’s start with it. Well known set of sentences showing problems of ambiguity and common-sense knowledge was made by Terry Winograd, it is called Winograd Schemas.
Let’s take one sentence from it - “Paul tried to call George on the phone, but he wasn’t available.” Who was not available?
The question seems obvious to people, but computers don’t know how the process of calling someone works, so without this knowledge it’s impossible to understand the sentence.
There are different kinds of ambiguity, but mostly they arise from the simplifications people make because they assume that everyone has the same commonsense knowledge.
Commonsense knowledge
.
Technical Details
-