Entity relation detection is a form of information extraction that finds predefined relations between pairs of entities in text. This paper describes a relation detection approach that combines clues from different levels of syntactic processing using kernel methods. Information from three different levels of processing is considered: tokenization, sentence parsing and deep dependency analysis. Each source of information is represented by kernel functions. Then composite kernels are developed to integrate and extend individual kernels so that processing errors occurring at one level can be overcome by information from other levels. We present an evaluation of these methods on the 2004 ACE relation detection task, using Support Vector Machines, and show that each level of syntactic processing contributes useful information for this task. When evaluated on the official test data, our approach produced very competitive ACE value scores. We also compare the SVM with KNN on different kernels.

No abstract

No abstract

Background: The current outbreak of COVID-19 has spread rapidly all over the world. Respiratory droplets and contaction with infected patients are the two major transmission routes. However, the value of tear virus nucleic acid is still not clear. We dynamic detected the SARS-CoV-2 in eye sample of one COVID-19 patient with obstruction of common lacrimal ducts. Methods: Besides the routine examination, nasopharyngeal and eye swab were continuously measured by polymerase chain reaction assay and next-generation sequencing (NGS). Gene detection was performed for drug use guidance, and flow cytometry was performed to analyse the lymphocyte subsets. Results: Nasopharyngeal swabs were positive for 22 days, but eye swabs were still continuously positive for 2 weeks after nasopharyngeal swabs turned negative. The low level of lymphocyte and the high level IL-6 lasted for almost 4 weeks, then became near normal. Next-generation sequencing (NGS) confirmed the existing of SARS-CoV-2, HSV1 and HHV6B virus nucleic acid. The gene detection for drug use guidance showed the genetic locus ABCB1 (3435T>C) rs1045642 belonged to type CC and it mean the efficiency of lopinavir-ritonavir would be significantly decreased. The flow cytometry of lymphocyte subsets showed PD-1 + CD95 + cells was accounting for 94.8% in CD3 + CD8 + T subset and for 94.8% in CD3 + TCRcd + T subset. Conclusions: As obstruction of common lacrimal duct, positively detection in one eye for 2 weeks more after nasopharyngeal swab became negative. More eye swabs should be collected from COVID-19 patients, especially from those immunocompromised, those with eye symptoms and those had a history of ocular diseases.