Pyramidal Recurrent Unit for Language Modeling
This addresses the issue of parameter efficiency and generalization in language modeling for NLP researchers, representing an incremental improvement over existing RNN methods.
The paper tackles the problem of poor generalizability in high-dimensional language modeling by introducing the Pyramidal Recurrent Unit (PRU), which improves perplexity by up to 1.3 points while reducing parameters by 15-20% compared to a state-of-the-art model.
LSTMs are powerful tools for modeling contextual information, as evidenced by their success at the task of language modeling. However, modeling contexts in very high dimensional space can lead to poor generalizability. We introduce the Pyramidal Recurrent Unit (PRU), which enables learning representations in high dimensional space with more generalization power and fewer parameters. PRUs replace the linear transformation in LSTMs with more sophisticated interactions including pyramidal and grouped linear transformations. This architecture gives strong results on word-level language modeling while reducing the number of parameters significantly. In particular, PRU improves the perplexity of a recent state-of-the-art language model Merity et al. (2018) by up to 1.3 points while learning 15-20% fewer parameters. For similar number of model parameters, PRU outperforms all previous RNN models that exploit different gating mechanisms and transformations. We provide a detailed examination of the PRU and its behavior on the language modeling tasks. Our code is open-source and available at https://sacmehta.github.io/PRU/