Year: 2020
Type: article
Abstract: 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.
Authors: Andrea Galassi, Marco Lippi, Paolo Torroni
Institutions: University of Bologna, University of Modena and Reggio Emilia
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,045
Funder: Horizon 2020 Framework Programme
Award: G5163439141
OpenAlex ID: W3031696893
