Evaluating Transformer Models and Human Behaviors on Chinese Character Naming
This work addresses the challenge of modeling grapheme-phoneme mapping in non-alphabet languages like Chinese for cognitive science and AI applications, though it is incremental as it extends existing methods to a new domain.
The study tackled the problem of evaluating how well transformer models capture human behavior in naming unknown Chinese characters, finding that models and humans had similar accuracy distributions, substantial answer overlap, and high correlation in their responses.
Neural network models have been proposed to explain the grapheme-phoneme mapping process in humans for many alphabet languages. These models not only successfully learned the correspondence of the letter strings and their pronunciation, but also captured human behavior in nonce word naming tasks. How would the neural models perform for a non-alphabet language (e.g., Chinese) unknown character task? How well would the model capture human behavior? In this study, we first collect human speakers' answers on unknown character naming tasks and then evaluate a set of transformer models by comparing their performances with human behaviors on an unknown Chinese character naming task. We found that the models and humans behaved very similarly, that they had similar accuracy distribution for each character, and had a substantial overlap in answers. In addition, the models' answers are highly correlated with humans' answers. These results suggested that the transformer models can well capture human's character naming behavior.