No abstract

Event detection is a fundamental task in information extraction. Most previous approaches typically view event detection as a triggerbased classification problem, focusing on using syntactic dependency structure or external knowledge to boost the classification performance. To overcome the inherent issues with existing trigger classification based models, we propose a novel approach to event detection by formulating it as a graph parsing problem, which can explicitly model the multiple event correlations and naturally utilize the rich information conveyed by event type and subtype. Furthermore, to cope with data sparsity, we employ a pretrained sequence-tosequence (seq2seq) model to transduce an input sentence into an accurate event graph without the need for trigger words. Extensive experimental results on the public ACE2005 dataset show that, our approach outperforms all previous state-of-the-art models for event detection by a large margin, obtaining an improvement of 4.2% F1 score. The result is very encouraging since we achieve this with a conceptually simple seq2seq model; moreover, by extending the graph structure, this proposed architecture can be flexibly applied to more information extraction problems for sentences.

No abstract

Background: To analyze the clinical characteristics of IgG4 related diseases (IgG4-RD), identify the most commonly used therapeutic drugs, and explore the potential tumor markers of IgG4-RD. Methods: 92 patients with IgG4 related diseases hospitalized in the Affiliated Hospital of Qingdao University from January 1, 2017 to December 31, 2021 were selected as the research object through the Yidu cloud system. Their clinical data were summarized and analyzed to summarize the clinical characteristics of IgG4-RD.Results: The age of diagnosis of IgG4 related diseases in this group was 31-84 years old, and the average age of diagnosis was (58.098 ± 11.344) years old, including 65 males (70.65%) and 27 females (29.35%). The most frequently involved organs and tissues were lymph nodes (37 cases, accounting for 40.2%), pancreas (33 cases, accounting for 35.9%), and salivary glands (31 cases, accounting for 33.7%). In this group, 28 cases (30.4%) were involved in single organ tissue, 32 cases (34.8%) were involved in double organ and multiple organ, respectively. 91 patients were treated with hormone for IgG4 related diseases, and 71 patients were treated with immunosuppressive agents, of which 45 cases were treated with cyclophosphamide (63.38%). In this group, the proportion of IgG4 level greater than 40g / L in tumor patients (18.18%) was significantly higher than that in non tumor patients (1.23%) (P < 0.05). Conclusion: The incidence of IgG4 related diseases is more common in middle-aged and elderly men, and the patients with lymph node, salivary gland and pancreas are more common. About 2 / 3 of the patients are double organ and multi organ patients. The most common rheumatic complications in patients with IgG4-RD are primary biliary cirrhosis, rheumatoid arthritis and Sjogren's syndrome. The most common tumor in patients with IgG4-RD is malignant tumor of digestive system. IgG4 levels greater than 40g/l in patients with IgG4 related diseases may be a potential indicator for predicting IgG4-RD associated tumors.