Search

This paper examines how to apply deep learning techniques to Mongolian bar exam questions. Several approaches that utilize eight different fine-tuned transformer models were demonstrated for recognizing textual inference in Mongolian bar exam questions. Among eight different models, the fine-tuned bert-base-multilingual-cased obtained the best accuracy of 0.7619. The fine-tuned bert-base-multilingual-cased was capable of recognizing “contradiction”, with a recall of 0.7857 and an F1 score of 0.7674; it recognized “entailment” with a precision of 0.7750, a recall of 0.7381, and an F1 score of 0.7561. Moreover, the fine-tuned bert-large-mongolian-uncased showed balanced performance in recognizing textual inference in Mongolian bar exam questions, thus achieving a precision of 0.7561, a recall of 0.7381, and an F1 score of 0.7470 for recognizing “contradiction”.

Abstract Hyperphosphatemia associated with chronic kidney disease (CKD) not only dysregulates mineral metabolism and bone diseases, but also strongly contributes to the progression of kidney disease itself. We have identified a novel drug for hyperphosphatemia, EOS789, that interacts with several sodium‐dependent phosphate transporters (NaPi‐IIb, PiT‐1, and PiT‐2) known to contribute to intestinal phosphate absorption. In this study, we investigated whether EOS789 could ameliorate kidney disease progression in glomerulonephritis rats. Anti‐glomerular basement membrane (GBM) nephritis was induced in rats by intravenously administering two types of anti‐rat GBM antibodies. We evaluated the effect of EOS789 administered in food admixture on hyperphosphatemia and kidney disease progression. In an anti‐GBM nephritis rats, which exhibit a significant increase in serum phosphate and a decline in renal function, EOS789 dose‐dependently improved hyperphosphatemia and EOS789 at 0.3% food admixture significantly ameliorated kidney dysfunction as shown in the decline of serum creatinine and BUN. Renal histopathology analysis showed that EOS789 significantly decreased crescent formation in glomeruli. To elucidate the mechanism underlying glomerular disease progression, human mesangial cells were used. High phosphate concentration in media significantly increased the expression of Collagen 1A1, 3A1, and αSMA mRNA in human mesangial cells and EOS789 dose‐dependently suppressed these fibrotic markers. These results indicate that EOS789 prevented glomerular crescent formation caused by mesangial fibrosis by ameliorating hyperphosphatemia. In conclusion, EOS789 would not only be useful against hyperphosphatemia but may also have the potential to relieve mesangial proliferative glomerulonephritis with crescent formation.

After producing triple (Gal, H-D and Sda)-KO pigs, hyperacute rejection appeared to no longer be a problem. However, the origin of xeno-rejection continues to be a controversial topic, including small amounts of antibodies and subsequent activation of the graft endothelium, the complement recognition system and the coagulation systems. The complement is activated via the classical pathway by non-Gal/H-D/Sda antigens and by ischemia-reperfusion injury (IRI), via the alternative pathway, especially on islets, and via the lectin pathway. The complement system therefore is still an important recognition and effector mechanism in xeno-rejection. All complement regulatory proteins (CRPs) regulate complement activation in different manners. Therefore, to effectively protect xenografts against xeno-rejection, it would appear reasonable to employ not only one but several CRPs including anti-complement drugs. The further assessment of antigens continues to be an important issue in the area of clinical xenotransplantation. The above conclusions suggest that the expression of sufficient levels of human CRPs on Triple-KO grafts is necessary. Moreover, multilateral inhibition on local complement activation in the graft, together with the control of signals between macrophages and lymphocytes is required.

Xenotransplantation is very attractive strategy for addressing the shortage of donors. While hyper acute rejection (HAR) caused by natural antibodies and complement has been well defined, this is not the case for innate cellular xenogeneic rejection. An increasing body of evidence suggests that innate cellular immune responses contribute to xenogeneic rejection. Various molecular incompatibilities between receptors and their ligands across different species typically have an impact on graft outcome. NK cells are activated by direct interaction as well as by antigen dependent cellular cytotoxicity (ADCC) mechanisms. Macrophages are activated through various mechanisms in xenogeneic conditions. Macrophages recognize CD47 as a “marker of self” through binding to SIRPα. A number of studies have shown that incompatibility of porcine CD47 against human SIRPα contributes to the rejection of xenogeneic target cells by macrophages. Neutrophils are an early responder cell that infiltrates xenogeneic grafts. It has also been reported that neutrophil extracellular traps (NETs) activate macrophages as damage-associated pattern molecules (DAMPs). In this review, we summarize recent insights into innate cellular xenogeneic rejection.

Digital archives (DAs) usually store diverse expert-level materials. Nowadays, access to DAs is increasing for non-expert users, However, they might have difficulties formulating appropriate search queries to find the necessary information. In response to this problem, we propose a query log-based query recommendation algorithm that provides expert knowledge to non-expert users, thus supporting their information seeking in DAs. The use case considered is one where after users enter some general queries, they will be recommended semantically similar expert-level queries in the query logs. The proposed modified conditional restricted Boltzmann machines (M-CRBMs) are capable of utilizing the rich metadata in DAs, thereby alleviating the sparsity problem that conventional restricted Boltzmann machines (RBMs) will face. Additionally, compared with other CRBM models, we drop a large number of model weights. In the experiments, the M-CRBMs outperform the conventional RBMs when using appropriate metadata, and we find that the recommendation results are relevant to the metadata fields that are used in M-CRBMs. Through experiments on the Europeana dataset, we also demonstrate the versatility and scalability of our proposed model.

In recent years, artworks have been increasingly digitized and built into databases, and such databases have become convenient tools for researchers. Researchers who retrieve artwork are not only researchers of humanities, but also researchers of materials science, physics, art, and so on. It may be difficult for researchers of various fields whose studies focus on the colors of artwork to find the required records in existing databases, that are color-based and only queried by the metadata. Besides, although some image retrieval engines can be used to retrieve artwork by text description, the existing image retrieval systems mainly retrieve the main colors of the images, and rare cases of color use are difficult to find. This makes it difficult for many researchers who focus on toning, colors, or pigments to use search engines for their own needs. To solve the two problems, we propose a cross-modal multi-task fine-tuning method based on CLIP (Contrastive Language-Image Pre-Training), which uses the human sensory characteristics of colors contained in the language space and the geometric characteristics of the sketches of a given artwork in order to gain better representations of that artwork piece. The experimental results show that the proposed retrieval framework is efficient for intuitively searching for rare colors, and that a small amount of data can improve the correspondence between text descriptions and color information.

This paper introduces a framework for retrieving low-resource font typeface databases by handwritten input. A new deep learning model structure based on metric learning is proposed to extract the features of a character typeface and predict the category of handwrittten input queries. Rather than using sufficient training data, we aim to utilize ancient character font typefaces with only one sample per category. Our research aims to achieve decent retrieval performances over more than 600 categories of handwritten characters automatically. We consider utilizing generic handcrafted features to train a model to help the voting classifier make the final prediction. The proposed method is implemented on the ‘Shirakawa font oracle bone script’ dataset as an isolated ancient-character-recognition system based on free ordering and connective strokes. We evaluate the proposed model on several standard character and symbol datasets. The experimental results showed that the proposed method provides good performance in extracting the features of symbols or characters’ font images necessary to perform further retrieval tasks. The demo system has been released, and it requires only one sample for each character to predict the user input. The extracted features have a better effect in finding the highest-ranked relevant item in retrieval tasks and can also be utilized in various technical frameworks for ancient character recognition and can be applied to educational application development.

In this paper, we proposed a method to generate two different types of reading comprehension questions complying with types of question for language learning tests with the Transformer model and the seq2seq method. In recent years, many approaches have showed good results by treating question generation as a seq2seq task. These approaches were implemented with a question-answering (QA) dataset; however, few studies have considered a reading comprehension-based dataset. Therefore, this paper proposed a method to generate questions appropriate for reading comprehension tests from articles. Moreover, analysis of reading comprehension test questions revealed two primary types of the question's asking style: the commonly-used question (CM question) and the directly-related question (DR question). The characteristic of the two question types was different and therefore needs to design the generation models complying with the type of questions. We proposed a method to separate the two question types in the dataset and used two models to generate both types, comparing the result with the method that generates the two types of questions together. The positive rate for the proposed method's CM questions was 88% and for its DR questions was 49%, compared to 33% and 24%, respectively, for the comparative method. The evaluation showed that the proposed method could generate the two types of reading comprehension questions more effectively, with a positive rate increased by an average of 40%. [ABSTRACT FROM AUTHOR]

Objective: Innate immunity plays a vital role in xenotransplantation. A CD47 molecule, binding to the SIRPa expressed on monocyte/macrophage cells, can suppress cytotoxicity. Particularly, the SIRPa contains ITIM, which delivers a negative signal. Our previous study demonstrated that the binding between CL-P1 and surfactant protein-D hybrid (CL-SP-D) with SIRPa regulates macrophages' phagocytic activity. In this study, we examined the effects of human CD47 and CL-SP-D expression on the inhibition of xenograft rejection by neutrophils in swine endothelial cells (SECs). Methods: We first examined SIRPa expression on HL-60 cells, a neutrophil-like cell line, and neutrophils isolated from peripheral blood. CD47-expressing SECs or CL-SP-D-expressing SECs were generated through plasmid transfection. Subsequently, these SECs were co-cultured with HL-60 cells or neutrophils. After co-culture, the degree of cytotoxicity was calculated using the WST-8 assay. The suppressive function of CL-SP-D on neutrophils was subsequently examined, and the results were compared with those of CD47 using naïve SECs as controls. Additionally, we assessed ROS production and neutrophil NETosis. Results: In initial experiments, the expression of SIRPa on HL-60 and neutrophils was confirmed. Exposure to CLSP-D significantly suppressed the cytotoxicity in HL-60 (p = 0.0038) and neutrophils (p = 0.00003). Furthermore, engagement with CD47 showed a suppressive effect on neutrophils obtained from peripheral blood (p = 0.0236) but not on HL-60 (p = 0.4244). The results of the ROS assays also indicated a significant downregulation of SEC by CD47 (p = 0.0077) or CL-SP-D (p = 0.0018). Additionally, the suppression of NETosis was confirmed (p = 0.0125) in neutrophils co-cultured with S/CL-SP-D. Conclusion: These results indicate that CL-SP-D is highly effective on neutrophils in xenogeneic rejection. Furthermore, CL-SP-D was more effective than CD47 at inhibiting neutrophil-mediated xenograft rejection. [ABSTRACT FROM AUTHOR]