Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Priming

arXiv:2405.09508v1 Announce Type: cross
Abstract: This study evaluates the performance of Recurrent Neural Network (RNN) and Transformer 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. Additionally, we utilize large language models (LLM) to measure …

abstract architectures arxiv bilingual chinese cs.cl cs.lg english human key language language processing languages modeling network neural network performance processing recurrent neural network rnn study transformer type