Introduction to Transformers: an NLP Perspective
It provides an introductory overview for those new to Transformers in NLP, but is incremental as it does not present new research.
This paper introduces basic concepts and key techniques of Transformers in NLP, summarizing their architecture, refinements, applications, strengths, and limitations.
Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes a description of the standard Transformer architecture, a series of model refinements, and common applications. Given that Transformers and related deep learning techniques might be evolving in ways we have never seen, we cannot dive into all the model details or cover all the technical areas. Instead, we focus on just those concepts that are helpful for gaining a good understanding of Transformers and their variants. We also summarize the key ideas that impact this field, thereby yielding some insights into the strengths and limitations of these models.