Search

Joint Multimodal Aspect-based Sentiment Analysis (JMASA) is a significant task in the research of multimodal fine-grained sentiment analysis, which combines two subtasks: Multimodal Aspect Term Extraction (MATE) and Multimodal Aspect-oriented Sentiment Classification (MASC). Currently, most existing models for JMASA only perform text and image feature encoding from a basic level, but often neglect the in-depth analysis of unimodal intrinsic features, which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features. Given this problem, we propose a Text-Image Feature Fine-grained Learning (TIFFL) model for JMASA. First, we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text, which addresses the context interference problem of identifying different aspect terms. Then, the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive, which addresses the ambiguous semantic extraction problem during image feature learning. Thereby, the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced. Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA, MATE and MASC, thus validating the effectiveness of our proposed methods. [ABSTRACT FROM AUTHOR]

Inductive link prediction (ILP) in knowledge graphs (KGs) aims to predict missing links between entities that were not seen during the training phase. Recent some subgraph-based methods have shown some advancements, but they all overlook the relational semantics between entities during subgraph extraction. To overcome this limitation, we introduce a novel inductive link prediction model named SASILP (Structure and Semantic Inductive Link Prediction), which comprehensively incorporates relational semantics in both subgraph extraction and node initialization processes. The model employs a random walk strategy to calculate the structural scores of neighboring nodes and utilizes an enhanced graph attention network to determine their semantic scores. By integrating both structural and semantic scores, SASILP strategically selects key nodes to form a subgraph. Furthermore, the subgraph is initialized with a node initialization technique that integrates information about neighboring relations. The experiments conducted on benchmark datasets demonstrate that SASILP outperforms state-of-the-art methods on inductive link prediction tasks, and verify the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Aspect-based multimodal sentiment analysis (ABMSA) is an emerging task in the research of multimodal sentiment analysis, which aims to identify the sentiment of each aspect mentioned in multimodal sample. Although recent research on ABMSA has achieved some success, most existing models only adopt attention mechanism to interact aspect with text and image respectively and obtain sentiment output through multimodal concatenation, they often neglect to consider that some samples may not have semantic relevance between text and image. In this article, we propose a Text-Image Semantic Relevance Identification (TISRI) model for ABMSA to address the problem. Specifically, we introduce a multimodal feature relevance identification module to calculate the semantic similarity between text and image, and then construct an image gate to dynamically control the input image information. On this basis, an image auxiliary information is provided to enhance the semantic expression ability of visual feature representation to generate more intuitive image representation. Furthermore, we employ attention mechanism during multimodal feature fusion to obtain the text-aware image representation through text-image interaction to prevent irrelevant image information interfering our model. Experiments demonstrate that TISRI achieves competitive results on two ABMSA Twitter datasets, and then validate the effectiveness of our methods. [ABSTRACT FROM AUTHOR]

Background: Ovarian cancer is the most lethal gynecological cancer which is characterized by extensive peritoneal implantation metastasis and malignant ascites. Despite advances in diagnosis and treatment in recent years, the five-year survival rate is only 25–30%. Therefore, developing multifunctional nanomedicine with abilities of promoting apoptosis and inhibiting migration on tumor cells would be a promising strategy to improve the antitumor effect. Methods and results: In this study, we developed a novel ACaT nanomedicine composed of alendronate, calcium ions and cyclin-dependent kinase 7 (CDK7) inhibitor THZ1. With the average size of 164 nm and zeta potential of 12.4 mV, the spherical ACaT nanoparticles were selectively internalized by tumor cells and effectively accumulated in the tumor site. Results of RNA-sequencing and in vitro experiments showed that ACaT promoted tumor cell apoptosis and inhibited tumor cell migration by arresting the cell cycle, increasing ROS and affecting calcium homeostasis. Weekly intraperitoneally administered of ACaT for 8 cycles significantly inhibited the growth of tumor and prolonged the survival of intraperitoneal xenograft mice. Conclusion: In summary, this study presents a new self-assembly nanomedicine with favorable tumor targeting, antitumor activity and good biocompatibility, providing a novel therapeutic strategy for advanced ovarian cancer. [ABSTRACT FROM AUTHOR]

Background: Prostate cancer (PCa) is the second most common cancer among males in the world and the majority of patients will eventually progress to the metastatic phase. How to choose an effective way for the treatment of metastatic PCa, especially in the later stage of the disease is still confusing. Herein we reported the case of a patient diagnosed with metastatic PCa and conducted a literature review on this issue. Case Presentation: A 57-year-old man with metastatic PCa had been managed by Dr. J.P. since April 2012 when the patient was admitted to the Third Affiliated Hospital of Sun Yat-sen University by aggravating frequent urination and dysuria. The prostate-specific antigen (PSA) concentration was 140 ng/ml, and the diagnosis of PCa was confirmed by prostate biopsy, with Gleason score 4 + 5 = 9. Chest CT and bone scan indicated multiple metastases in the lungs and bones. Triptorelin, bicalutamide, zoledronic acid, and docetaxel were then administered, six cycles later, the metastatic tumors in the lungs disappeared and those in the bones lessened significantly, along with a remarkable reduction in PSA level (< 2 ng/ml). Intermittent androgen deprivation was subsequently conducted until August 2018, when the serum PSA level was found to be 250 ng/ml, again docetaxel 75 mg/m2 was administered immediately but the patient was intolerant this time. Instead, abiraterone was administered until March 2019 because of intolerable gastrointestinal side-effects and increasing PSA level. In October 2019, the patient came to our center, a modified approach of docetaxel (day 1 40 mg/m2 + day 8 35 mg/m2) was administered. Luckily, the PSA level decreased rapidly, the bone pain was greatly relieved, and no obvious side effects occurred. However, four cycles later, docetaxel failed to work anymore, the metastatic tumor in the liver progressed. We proposed several regimens as alternatives, but they were soon denied due to the high prices or unavailability or uncertain effect of the drugs. In addition, the patient's condition deteriorated speedily and can no longer bear any aggressive treatment. Finally, the patient died of multiple organ failure in August 2020. Conclusion: The experiences of this case provide valuable evidence and reference for the treatment choices of metastatic PCa, in some circumstances modified and advanced regimens may produce unexpected effects. [ABSTRACT FROM AUTHOR]