Memory Transformer (2006.11527v2)

Abstract: Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware representations. However, information about the context is stored mostly in the same element-wise representations. This might limit the processing of properties related to the sequence as a whole more difficult. Adding trainable memory to selectively store local as well as global representations of a sequence is a promising direction to improve the Transformer model. Memory-augmented neural networks (MANNs) extend traditional neural architectures with general-purpose memory for representations. MANNs have demonstrated the capability to learn simple algorithms like Copy or Reverse and can be successfully trained via backpropagation on diverse tasks from question answering to LLMing outperforming RNNs and LSTMs of comparable complexity. In this work, we propose and study few extensions of the Transformer baseline (1) by adding memory tokens to store non-local representations, (2) creating memory bottleneck for the global information, (3) controlling memory update with dedicated layer. We evaluate these memory augmented Transformers and demonstrate that presence of memory positively correlates with the model performance for machine translation and LLMling tasks. Augmentation of pre-trained masked LLM with memory tokens shows mixed results for tasks from GLUE benchmark. Visualization of attention patterns over the memory suggest that it improves the model's ability to process a global context.