Title: Adaptive Semiparametric Language Models
Authors: Dani Yogatama, Cyprien de Masson d’Autume, Lingpeng Kong
Published: 4th February 2021 (Thursday) @ 11:47:03
Link: http://arxiv.org/abs/2102.02557v1
Abstract
We present a language model that combines a large parametric neural network (i.e., a transformer) with a non-parametric episodic memory component in an integrated architecture. Our model uses extended short-term context by caching local hidden states — similar to transformer-XL — and global long-term memory by retrieving a set of nearest neighbor tokens at each timestep. We design a gating function to adaptively combine multiple information sources to make a prediction. This mechanism allows the model to use either local context, short-term memory, or long-term memory (or any combination of them) on an ad hoc basis depending on the context. Experiments on word-based and character-based language modeling datasets demonstrate the efficacy of our proposed method compared to strong baselines.