摘要：Knowledge graph (KG) completion aims at filling the missing facts in a KG, where a fact is typically represented as a triple in the form of (head, relation, tail). Traditional KG completion methods compel two#2;thirds of a triple provided (e.g., head and relation) to predict the remaining one. In this paper, we propose a new method that extends multi-layer recurrent neural networks (RNNs) to model triples in a KG as sequences. It obtains state-of-the-art performance on the common entity prediction task, i.e., giving head (or tail) and relation to predict the tail (or the head), using two benchmark data sets. Furthermore, the deep sequential characteristic of our method enables it to predict the relations given head (or tail) only, and even predict the whole triples. Our experiments on these two new KG completion tasks demonstrate that our method achieves superior performance compared with several alternative methods.
摘要： We noticed an unusual increase of first-time patients with schizophrenia (F20) in January 2020 since the outbreak of COVID-19. The aim of this retrospective study is to validate this observation and find potential risk factors, if applicable. A total number of 13,783 records from outpatients in January 2020 were investigated thoroughly. Comparisons between incidence of schizophrenia in outpatients in January 2020 and similar periods of 2017-2019 were made to minimize seasonal influence. Relationship of incidence of schizophrenia and COVID-19 infections in China was calculated. Limited personal information (age, gender, approximate residence) was analyzed to find risk factors.After excluding seasonal factors such as Spring festival, a positive relationship between incidence of schizophrenia in first-time patients and countrywide epidemic situation was found. Statistical results further showed a significant increase of median age from 39 to 50 for first-time patients diagnosed with schizophrenia which is unusual. Meanwhile, a slight but not significant change was found in distribution of gender and approximate residence (urban/suburb). Our data supported that COVID-19 outbreak increased risk of schizophrenia in aged adults which is consistent with the fact that COVID-19 is more lethal to elders. We strongly appeal that public healthcare in countries either with or without infected patients should prepare in advance for potential risks in public mental health.