Lattice Recurrent Unit: Improving Convergence and Statistical Efficiency for Sequence Modeling

Code

• github.com/chahuja/lru
  OfficialIn paperpytorch★ 0
• github.com/MindCode-4/code-7/tree/main/lru
  mindspore★ 0
• github.com/MindSpore-scientific/code-6/tree/main/lru
  mindspore★ 0

Abstract

Recurrent neural networks have shown remarkable success in modeling sequences. However low resource situations still adversely affect the generalizability of these models. We introduce a new family of models, called Lattice Recurrent Units (LRU), to address the challenge of learning deep multi-layer recurrent models with limited resources. LRU models achieve this goal by creating distinct (but coupled) flow of information inside the units: a first flow along time dimension and a second flow along depth dimension. It also offers a symmetry in how information can flow horizontally and vertically. We analyze the effects of decoupling three different components of our LRU model: Reset Gate, Update Gate and Projected State. We evaluate this family on new LRU models on computational convergence rates and statistical efficiency. Our experiments are performed on four publicly-available datasets, comparing with Grid-LSTM and Recurrent Highway networks. Our results show that LRU has better empirical computational convergence rates and statistical efficiency values, along with learning more accurate language models.

Reproductions