Advancing Regular Language Reasoning in Linear Recurrent Neural Networks

arXiv:2309.07412v2 Announce Type: replace-cross
Abstract: In recent studies, linear recurrent neural networks (LRNNs) have achieved Transformer-level performance in natural language and long-range modeling, while offering rapid parallel training and constant inference cost. With the resurgence of interest in LRNNs, we study whether they can learn the hidden rules in training sequences, such as the grammatical structures of regular language. We theoretically analyze some existing LRNNs and discover their limitations in modeling regular language. Motivated by this analysis, we propose a …

arxiv cs.cl cs.lg language linear networks neural networks reasoning recurrent neural networks type