What artificial intelligence might teach us about the origin of human language
This research addresses the problem of understanding potential evolutionary origins of human language biases for linguists and cognitive scientists, but it is incremental as it builds on existing sound symbolism and error management theory.
The study investigates how AI models learning sound symbolism exhibit a bias towards overpredicting categories associated with greater threat, proposing this as evidence for an adaptation favoring cautious behavior, and tests this by analyzing classification errors in XGBoost models using Pokemon names from Chinese, Japanese, and Korean languages.
This study explores an interesting pattern emerging from research that combines artificial intelligence with sound symbolism. In these studies, supervised machine learning algorithms are trained to classify samples based on the sounds of referent names. Machine learning algorithms are efficient learners of sound symbolism, but they tend to bias one category over the other. The pattern is this: when a category arguably represents greater threat, the algorithms tend to overpredict to that category. A hypothesis, framed by error management theory, is presented that proposes that this may be evidence of an adaptation to preference cautious behaviour. This hypothesis is tested by constructing extreme gradient boosted (XGBoost) models using the sounds that make up the names of Chinese, Japanese and Korean Pokemon and observing classification error distribution.