Natural Language Processing Meets Quantum Physics: A Survey and Categorization

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3172–3182 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 3172 Natural Language Processing Meets Quantum Physics: A Survey and Categorization Sixuan Wu1,2, Jian Li3, Peng Zhang4 and Yue Zhang2,5 1Fudan University 2School of Engineering, Westlake University 3School of Science, Westlake University 4College of Intelligence and Computing, Tianjin University 5Institute of Advanced Technology, Westlake Institute for Advanced Study Abstract Recent research has investigated quantum NLP, designing algorithms that process nat- ural language in quantum computers, and also quantum-inspired algorithms that im- prove NLP performance on classical comput- ers. In this survey, we review representative methods at the intersection of NLP and quan- tum physics in the past ten years, categorizing them according to the use of quantum theory, the linguistic targets that are modeled, and the downstream application. The literature review ends with a discussion on the key factors to the success that has been achieved by exist- ing work, as well as challenges ahead, with the goal of better understanding the promises and further directions. 1 Introduction Quantum computing has received much interest in recent years. The basic idea is to make use the power of quantum mechanics for solving computa- tional problems (Shor, 1999; Nielsen and Chuang, 2002). While particular quantum algorithms can be substantially faster alternatives to classical counter- parts (Biamonte et al., 2017; Arute et al., 2019), the mathematical framework of quantum physics has also been exploited for cognition (Busemeyer and Bruza, 2012), optimization (Soleimanpour et al., 2014) and other disciplines. In the field of natural language processing (NLP), quantum mechanics has seen a surge of recent research interests, ad- dressing problems ranging from lexical semantic ambiguities (Meyer and Lewis, 2020) to seman- tic composition (Coecke et al., 2020), and from information retrieval (Jiang et al., 2020) to text classification (Zhang et al., 2021), where different characteristics of quantum physics have inspired novel algorithms. Despite its growing research literature, no sur- vey has reviewed and categorized the quantum NLP field. The most relevant surveys are on quantum- inspired information retrieval (Uprety et al., 2020; Melucci, 2015). However, they did not include many important findings in the quantum NLP field. Abohashima et al. (2020) and Garg and Ramakrish- nan (2020) generally reviewed the field of quantum machine learning. They also briefly mentioned sev- eral quantum algorithms for NLP, but they did not discuss them comprehensively or in detail. The goal of our paper is to, for the first time, propose a categorization of quantum NLP in the past ten years, aiming to provide the latest knowledge of developments and achievements in this field. We categorize existing work on quantum NLP based on the following three dimensions: 1 The types of algorithms. Many quantum- inspired NLP algorithms run on classical com- puters, and some quantum NLP algorithms can potentially be implemented on quantum hardware (Section 3). 2 The modeling target. Quantum physics is used for modeling different features of language (Section 4). 3 The applications. These …

Content truncated to 500 words