Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Priming
This work addresses the problem of understanding human cognitive processes in bilingual language processing for researchers in computational linguistics and cognitive science, though it is incremental as it compares existing models on a specific task.
This study tackled the problem of modeling cross-language structural priming in bilingual sentence processing by evaluating RNN and Transformer architectures, finding that transformers outperform RNNs with accuracy improvements of 25.84% to 33.33%.
This study evaluates the performance of Recurrent Neural Network (RNN) and Transformer models in replicating cross-language structural priming, a key indicator of abstract grammatical representations in human language processing. Focusing on Chinese-English priming, which involves two typologically distinct languages, we examine how these models handle the robust phenomenon of structural priming, where exposure to a particular sentence structure increases the likelihood of selecting a similar structure subsequently. Our findings indicate that transformers outperform RNNs in generating primed sentence structures, with accuracy rates that exceed 25.84\% to 33. 33\%. This challenges the conventional belief that human sentence processing primarily involves recurrent and immediate processing and suggests a role for cue-based retrieval mechanisms. This work contributes to our understanding of how computational models may reflect human cognitive processes across diverse language families.