Papers for

cognitive ai engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Machine learning gives new insight on how people understand word meanings

Cognitive Thermometers: Machine Learning and Logical Complexity

Abstract: How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on logical definability and complexity, but these are highly sensitive to the choice of logical language, rendering some design choices unmotivated. In this article, we propose that machine learning provides a somewhat more agnostic approach to measuring semantic complexity. We review emerging evidence that logic and machine learning often yield converging results on relative complexity and its resulting effects in semantic typology. Where they diverge, learning appears to be a better explanation than logical complexity. We argue that treating machine learning models as ``cognitive thermometers'' enables a unified approach to complexity that bridges symbolic logic and connectionist AI.

Wed 7 OctComputation and Language

The gist

How do people think about categories and meanings in language? Previous ideas used logic to explain this but depended too much on the type of logic used. The authors show that machine learning can measure how complicated meanings are in a way less tied to specific logic choices. They find that both logic and machine learning often agree, but when they don’t, machine learning better explains how meanings are organized in natural languages.

Open → 2610.10724v1