Traitement quantique des langues : {é}tat de l'art
This is an incremental review summarizing existing quantum NLP approaches for researchers in the field.
The article reviews quantum computing research for NLP, aiming to enhance model performance and better represent linguistic phenomena like ambiguity and long-range dependencies, with experimental studies shown to be feasible and opening new research perspectives.
This article presents a review of quantum computing research works for Natural Language Processing (NLP). Their goal is to improve the performance of current models, and to provide a better representation of several linguistic phenomena, such as ambiguity and long range dependencies. Several families of approaches are presented, including symbolic diagrammatic approaches, and hybrid neural networks. These works show that experimental studies are already feasible, and open research perspectives on the conception of new models and their evaluation.