Semantic Communications: A Paradigm Whose Time Has Come

Abstract

Communication system design to date is predicated on principles that abstract information as digital sequences irrespective of their meanings. Such a semantic-agnostic approach leads to fundamental limits that are application and technology independent, and offers efficient engineering of communication systems. Emerging applications that involve communications however, call for going beyond the engineering problem of reliably reconstructing a digital sequence. Most current communication devices are computing devices that execute tasks. Increasingly communication is needed for a purpose and is integrated with decision making, machine learning and sensing. Further, human networks operate over machine networks, which necessitate more sophisticated human-machine communication. The goal of this vision paper is to advocate for Semantic Communications, i.e., communication system design that, at the outset, pays attention to the content, its meaning, context, and purpose. We will argue that taking into account the meanings and context of information can lead to better communication designs. In particular, we argue in favor of semantic distortion, a novel metric introduced nearly a decade ago, based upon which communications systems design aiming to convey the meaning and purpose can be designed. We review the current efforts of Semantic Communications which has recently become a popular area of 6G, and potential directions of Semantic Communications, which can explore various different directions with novel metrics including using Knowledge Graphs (KL), information theoretic approaches, and machine/Deep Learning (DL).