Named entity recognition as a fundamental task plays a crucial role in accomplishing some of the tasks and applications in natural language processing. In the age of Internet information, as far as computer applications are concerned, a huge proportion of information is stored in structured and unstructured forms and used for language and text processing. Before neural networks were widely used in natural language processing tasks, research in the field of named entity recognition usually focused on leveraging lexical and syntactic knowledge to improve the performance of models or methods. To promote the development of named entity recognition, researchers have been creating named entity recognition datasets through conferences, projects, and competitions for many years, based on various research goals, and training entity recognition models with increasing accuracy on this basis. However, there has not been much exploration of named entity recognition datasets. Particularly, there have been many datasets available since the introduction of the named entity recognition task, but there is no clear framework to summarize the development of these seemingly independent datasets. A closer look at the context of the development of each dataset and the features it contains reveals that these datasets share some common features to varying degrees. In this thesis, we review the development of named entity recognition datasets over the years and describe them in terms of the language of the dataset, the domain of research, the type of entity, the granularity of the entity, and the annotation of the entity. Finally, we provide an idea for the creation of subsequent named entity recognition datasets.
For the emerging autonomous swarm technology, from the perspective of systems science and systems engineering, there must be some novel elements and methods to aggregate multiple systems into a group, which distinguish with the general components with specific functions, and we expect to provide the presentation of their existence in the swarm development processes. The inspiration of our methodology origins from the integration of swarm ontology, multi-paradigm modeling, multi-agent system, cyber-physical system, etc. Therefore, we choose the model-driven technology as a framework to acquire an approach of model representation across the multiple levels of abstraction and composition. The autonomous strategic mechanism is defined and formed in parallel with ConOps analysis and systems design, so as to effectively solve the cognitive problem of emergence caused by the nonlinear causation among individual and whole behaviors. This approach highlights to use the MBSE processes and their artifacts to embed the meso mechanism to integrate the operational and the functional, and which means to connect the macro and micro aspects in formalism and so to become a whole with its expected goals, and then to verify and validate within a L-V-C simulation environment.
Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research.