RESUMO
Over the years, the explosive growth of drug-related text information has resulted in heavy loads of work for manual data processing. However, the domain knowledge hidden is believed to be crucial to biomedical research and applications. In this article, the multi-DTR model that can accurately recognize drug-specific name by joint modeling of DNER and DNEN was proposed. Character features were extracted by CNN out of the input text, and the context-sensitive word vectors were obtained using ELMo. Next, the pretrained biomedical words were embedded into BiLSTM-CRF and the output labels were interacted to update the task parameters until DNER and DNEN would support each other. The proposed method was found with better performance on the DDI2011 and DDI2013 datasets.
Assuntos
Aprendizado Profundo , Redes Neurais de Computação , Projetos de PesquisaRESUMO
Research regarding the regional environmental regulation efficiency (ERE) and influencing factors can provide theoretical guidance for regions to improve their ERE effectively. By employing a two-step approach, the data envelopment analysis (DEA) CCR-BCC model is built with the inclusion of scale changes, and a Tobit model is developed to explore the influencing factors for the regional ERE, followed by an application to analyze the spatiotemporal variations of ERE in Jiangsu province from 2005 to 2015. It is found that in time dimension, the ERE lies generally in a weak effective interval of [0.5, 1) and displays a shock upward trend. In the spatial dimension, the ERE presents an obvious "bilateral effect", namely, the efficiency is high for both the southern and northern of Jiangsu province but lower for the middle area. Besides, GDP per capital, industrial structure, trade openness, and population growth are among the main influencing factors of ERE. The findings revealed that temporary short-term policies have noticeable impact on the regional ERE, and "matching effect" between the ERE and regional economic development does not present.
