Attention in Natural Language Processing
This work provides a foundational taxonomy for researchers in NLP to organize and understand the fast-paced advances in attention mechanisms, though it is incremental as it synthesizes existing work rather than introducing new methods.
The authors tackled the lack of a systematic overview of attention mechanisms in NLP by defining a unified model and proposing a taxonomy across four dimensions, resulting in the first extensive categorization of the literature in this domain.
Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for attention architectures in natural language processing, with a focus on those designed to work with vector representations of the textual data. We propose a taxonomy of attention models according to four dimensions: the representation of the input, the compatibility function, the distribution function, and the multiplicity of the input and/or output. We present the examples of how prior information can be exploited in attention models and discuss ongoing research efforts and open challenges in the area, providing the first extensive categorization of the vast body of literature in this exciting domain.