A Transformer with Stack Attention
This work addresses a fundamental modeling gap in transformer-based language models for natural language processing, though it is incremental as it only partially solves the problem.
The authors tackled the limitation of transformers in modeling context-free languages by proposing a stack-based attention mechanism, which enabled transformers to model some deterministic context-free languages but not all.
Natural languages are believed to be (mildly) context-sensitive. Despite underpinning remarkably capable large language models, transformers are unable to model many context-free language tasks. In an attempt to address this limitation in the modeling power of transformer-based language models, we propose augmenting them with a differentiable, stack-based attention mechanism. Our stack-based attention mechanism can be incorporated into any transformer-based language model and adds a level of interpretability to the model. We show that the addition of our stack-based attention mechanism enables the transformer to model some, but not all, deterministic context-free languages.