Position Information in Transformers: An Overview

Dufter, Philipp; Schmitt, Martin and Schütze, Hinrich (September 2022): Position Information in Transformers: An Overview. In: Computational Linguistics, Vol. 48, No. 3: pp. 733-763

Abstract

Transformers are arguably the main workhorse in recent natural language processing research. By definition, a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential and word order is essential to the semantics and syntax of an utterance. In this article, we provide an overview and theoretical comparison of existing methods to incorporate position information into Transformer models. The objectives of this survey are to (1) showcase that position information in Transformer is a vibrant and extensive research area; (2) enable the reader to compare existing methods by providing a unified notation and systematization of different approaches along important model dimensions; (3) indicate what characteristics of an application should be taken into account when selecting a position encoding; and (4) provide stimuli for future research.

• Item Type: Journal article
• EU Funded Grant Agreement Number: 740516
• EU Projects: Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement
• Form of publication: Publisher's Version
• Research Centers: Center for Information and Language Processing (CIS)
• Subjects: 400 Language > 400 Language; 400 Language > 410 Linguistics
• Language: English