In natural language processing, it is common that many entities contain other entities inside them. Most existing works on named entity recognition (NER) only deal with flat entities but ignore nested ones. We propose a boundary-aware neural model for nested NER which leverages entity boundaries to predict entity categorical labels. Our model can locate entities precisely by detecting boundaries using sequence labeling models. Based on the detected boundaries, our model utilizes the boundary-relevant regions to predict entity categorical labels, which can decrease computation cost and relieve error propagation problem in layered sequence labeling model. We introduce multitask learning to capture the dependencies of entity boundaries and their categorical labels, which helps to improve the performance of identifying entities. We conduct our experiments on nested NER datasets and the experimental results demonstrate that our model outperforms other state-of-the-art methods.
Long-term care (LTC) reflects a growing emphasis on person-centered care (PCC), with services oriented around individuals’ needs and preferences. Addressing contextual and cultural differences across countries offers important insight into factors that facilitate or hinder application of PCC practices within and across countries. This article takes an international lens to consider country-specific contexts of LTC, describing preliminary steps to develop common data elements that capture contextual differences across LTC settings globally. Through an iterative series of online, telephone, and in-person sessions, we engaged in in-depth discussions with 11 colleague experts in residential LTC and coauthors from six countries (China and Hong Kong, England, Sweden, Thailand, Trinidad and Tobago, and the United States). Our discussions yielded rich narrative describing a vast range in types of LTC settings, leading to our development of a working definition of residential LTC. Scope of services, funding, ownership, and regulations varied greatly across countries and across different residential LTC settings within countries. Moving forward, we recommend expanding our activities to countries that reflect different stages of residential LTC development. Our goal is to contribute to a larger initiative underway by the WE-THRIVE consortium to establish a global research measurement infrastructure that advances PCC internationally.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.