Recurrent Neural Networks In Linguistic Theory: Revisiting Pinker And Prince (1988) And The Past Tense Debate | Awesome LLM Papers Add your paper to Awesome LLM Papers

Recurrent Neural Networks In Linguistic Theory: Revisiting Pinker And Prince (1988) And The Past Tense Debate

Christo Kirov, Ryan Cotterell . Transactions of the Association for Computational Linguistics 2018 – 76 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
ACL Interdisciplinary Approaches Model Architecture Neural Machine Translation Security TACL Variational Autoencoders

Can advances in NLP help advance cognitive modeling? We examine the role of artificial neural networks, the current state of the art in many common NLP tasks, by returning to a classic case study. In 1986, Rumelhart and McClelland famously introduced a neural architecture that learned to transduce English verb stems to their past tense forms. Shortly thereafter, Pinker & Prince (1988) presented a comprehensive rebuttal of many of Rumelhart and McClelland’s claims. Much of the force of their attack centered on the empirical inadequacy of the Rumelhart and McClelland (1986) model. Today, however, that model is severely outmoded. We show that the Encoder-Decoder network architectures used in modern NLP systems obviate most of Pinker and Prince’s criticisms without requiring any simplication of the past tense mapping problem. We suggest that the empirical performance of modern networks warrants a re-examination of their utility in linguistic and cognitive modeling.

Similar Work