语言学理论中的循环神经网络：重审Pinker与Prince（1988）及过去式之争
Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate
AI总结：
本研究重审过去式之争经典案例，发现现代NLP的Encoder-Decoder网络可化解早年对神经模型的主要批评，支持重新评估神经网络在语言学与认知建模中的价值。
摘要：
自然语言处理（NLP）的进展能否推动认知建模的发展？我们通过回归一个经典案例研究，检验了人工神经网络（当前许多常见NLP任务的最优技术）的作用。1986年，Rumelhart和McClelland提出了一个著名的神经架构，该架构能够学习将英语动词词干转换为其过去式形式。不久之后，Pinker与Prince（1988）对Rumelhart和McClelland的诸多主张提出了全面反驳，他们的批判力度很大程度上集中于Rumelhart和McClelland（1986）模型的实证不足。然而如今，该模型已严重过时。我们表明，现代NLP系统中使用的Encoder-Decoder（编码器-解码器）网络架构无需对过去式映射问题做任何简化，就能化解Pinker和Prince的大部分批评。我们认为，现代网络的实证表现值得重新审视其在语言学和认知建模中的效用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
