A Survey on Named Entity Recognition Solutions Applied for Cybersecurity-Related Text Processing

Named entity recognition (NER) is one of the most common Natural Language Processing (NLP) tasks. As nowadays large quantities of unstructured data are produced, the organizations have begun to be more interested in NER solutions. In the first part of this article, we describe the evolution of NER, and we discuss the most common NER approaches. Later, we address the state-of-the-art NER machine learning solutions. We focus both on open-source and commercial solutions. The most important solutions are identified and compared based on a methodology proposed by the authors. Since the authors are involved in using NER on cybersecurity-related text, the study focuses mainly on NER aspects related to cybersecurity domain. Nevertheless, this survey has a general nature, and therefore, our conclusions can be useful as well for those interested in using NER solutions in other domains.