Relation Classification Research Articles

IBRIDGE: A Data Integration Method to Identify Inflamed Tumors from Single-cell RNA-Seq Data and Differentiate Cell Type-Specific Markers of Immune-Cell Infiltration.

The development of immune checkpoint-based immunotherapies has been a major advancement in the treatment of cancer, with a subset of patients exhibiting durable clinical responses. A predictive biomarker for immunotherapy response is the preexisting T-cell infiltration in the tumor immune microenvironment (TIME). Bulk transcriptomics-based approaches can quantify the degree of T-cell infiltration using deconvolution methods and identify additional markers of inflamed/cold cancers at the bulk level. However, bulk techniques are unable to identify biomarkers of individual cell types. Although single-cell RNA sequencing (scRNA-seq) assays are now being used to profile the TIME, to our knowledge there is no method of identifying patients with a T-cell inflamed TIME from scRNA-seq data. Here, we describe a method, iBRIDGE, which integrates reference bulk RNA-seq data with the malignant subset of scRNA-seq datasets to identify patients with a T-cell inflamed TIME. Using two datasets with matched bulk data, we show iBRIDGE results correlated highly with bulk assessments (0.85 and 0.9 correlation coefficients). Using iBRIDGE, we identified markers of inflamed phenotypes in malignant cells, myeloid cells, and fibroblasts, establishing type I and type II interferon pathways as dominant signals, especially in malignant and myeloid cells, and finding the TGFβ-driven mesenchymal phenotype not only in fibroblasts but also in malignant cells. Besides relative classification, per-patient average iBRIDGE scores and independent RNAScope quantifications were used for threshold-based absolute classification. Moreover, iBRIDGE can be applied to in vitro grown cancer cell lines and can identify the cell lines that are adapted from inflamed/cold patient tumors.

An appraisal on occlusal concepts and classifications of full mouth rehabilitation: A systematic review

Aim: The review would aim to provide an appraisal of the current understanding of occlusal concepts and their classification in relation to full mouth rehabilitation.Settings and Design: Systematic review following PRISMA guidelines.Materials and Methods: Two researchers looked through the first search results to weed out duplicates and studies that weren't pertinent to the research issue. When choosing the publications, the titles and abstracts were examined to find the pertinent studies. The full versions of these studies were then retrieved, and the third investigator evaluated them for inclusion and exclusion criteria. Additionally noted were the explanations for studies' exclusion. Finally, the studies that were chosen were those that provided answers to the review's queries.Age, gender, cause of occlusal wear, T&M classification of the clinical condition, applied occlusal scheme, practical applicability of the philosophy, assessment of vertical dimension of occlusion, treatment outcome, and patient comfort are the variables taken into account for the study.Statistical Analysis Used: Qualitative analyisis.Results: A total of 1143 studies were found which were screened and assessed for eligibility. Out of these 36 articles were full text articles. Of these 17 studies did not meet the eligibility criteria since they failed to mention the occlusal concept incorporated in full mouth rehabilitation procedure.Out of 19 included studies, 10 were Studies with Full mouth occlusal rehabilitation using Hobo’s twin stage technique, 8 were studies Included Studies with Full mouth occlusal rehabilitation using Pankeymann-Schuyler philosophy and only 1 study was Full mouth occlusal rehabilitation using other techniques. All the included studies were case reports; except one study, which was Case series.Conclusion: Efforts must be made to create a harmonious occlusal interface by accurately diagnosing the cause of disorders and making intra-oral alterations. The Turner & Misserlian categorization shows most cases to be category 1, treated with the canine-guided occlusal concept using the HOBO twin-stage philosophy. This method simplifies the procedure without sacrificing accuracy.

Edge-Labeled and Node-Aggregated Graph Neural Networks for Few-Shot Relation Classification

Relation classification as a core technique for building knowledge graphs becomes a critical task in natural language processing. The fact that humans can learn by summarizing and generalizing limited knowledge motivates scholars to explore few-shot learning. Graph neural networks provide a method to measure the distance between nodes, which improves the model effect in the problem of few-shot relation classification. However, graph neural network methods focus only on node information and ignore edge information which implies inter-class and intra-class relations. This paper proposes edge-labeled and node-aggregated graph neural networks (ENGNNs) for few-shot relation classification: edge labels are encoded and used for node information aggregation. In addition, a process of semi-supervised learning is designed to discover a better solution for one-shot learning. Compared with previous methods, experimental results show that the proposed ENGNN model improves the performance of the graph neural network on the FewRel dataset.

The Missing Gender: Examining the Barriers to Women’s Participation in Sports in India

The advent of modernity has changed the sports landscape of the world, wherein all barriers, especially gender discrimination, have been broken, with men and women competing shoulder to shoulder in the sports arena. However, the sports landscape in India is completely different, as all the major sports activities are dominated by men. The aim of this study is to classify and rank the barriers that deter women’s participation in sports in India. For achieving this objective, a multi-criteria decision-making technique of Interpretive Structural Modelling (ISM) and MICMAC analysis has been used for relative ranking and classification of barriers that lead to gender discrimination in sports in India. The study encapsulates significant barriers that hinder women from actively participating in sports in India. The findings of our study suggest that economic barriers, lack of sporting infrastructure and culture, lack of potential career opportunities, knowledge barriers, and socio-cultural barriers are vital reasons that have implications for limiting women’s participation in sports and society alike. From a policy perspective, the proposed model will help identify the key barriers that ought to be addressed to bridge the gap between men and women in the sports sector in India.

Few-shot relation classification using clustering-based prototype modification

Few-shot relation classification is a natural language processing task that aims to enable models to recognize new relational categories of query instances by training on base classes with few labeled support instances. Many recently proposed prototypical-network-based approaches have exhibited excellent performance, some of which include additional information to further improve the model performance further. However, existing methods ignore the category information hidden in the query set and the hierarchical information that exists in relational hyponymy and fail to address the fundamental problem whereby the obtained prototype is always unreliable owing to the limited instances in the support set. In this study, we propose a novel prototypical-network-based model for the few-shot relation classification task to generate more precise relational prototypes by taking advantage of the category information hidden in the query set. In the model, we design a novel relational-similarity-based instance adaptive local loss that leverages relational hierarchical information to distinguish the hard instances belonging to similar relations effectively. Experiments on the FewRel dataset demonstrate that our approach achieves state-of-the-art performance.

A joint training network for learning more distinguishable relation features in relation classification

Relation classification is an important task in natural language processing, which aims to predict the semantic relation between a given entity pair in a sentence. There are datasets, like TACRED, that contain a large number of “no_relation” type samples. Most existing methods treat “no_relation” and normal relation types equally, and directly apply the softmax function over all relation types. In this paper, we propose a novel joint training network to learn more distinguishable relation features for relation classification. Specially, we convert the original multi-class classification problem into two joint optimized modules, binary classification of whether a relation is “no_relation” and multi-class classification of normal relation types. To further differentiate between similar normal relation types, we introduce a self-supervised contrastive learning method to learn more distinguishable features for them. We jointly optimize the above modules. Experimental results agree well with our design intention and demonstrate that our joint training network not only achieves superior performance against existing competitive models, but also is robust to “no_relation” problem.

A Span-based Target-aware Relation Model for Frame-semantic Parsing

Frame-semantic Parsing (FSP) is a challenging and critical task in Natural Language Processing (NLP). Most of the existing studies decompose the FSP task into frame identification (FI) and frame semantic role labeling (FSRL) subtasks, and adopt a pipeline model architecture that clearly causes error propagation problem. However, recent jointly learning models aim to address the above problem and generally treat FSP as a span-level structured prediction task, which, unfortunately, leads to cascading error propagation problem between roles and less-efficient solutions due to huge search space of roles. To address these problems, we reformulate the FSRL task into a target-aware relation classification task and propose a novel and lightweight jointly learning framework that simultaneously processes three subtasks of FSP, including frame identification, argument identification, and role classification. The novel task formulation and jointly learning with interaction mechanisms among subtasks can help improve the overall system performance and reduce the search space and time complexity, compared with existing methods. Extensive experimental results demonstrate that our proposed model significantly outperforms 10 state-of-the-art models in terms of F1 score across two benchmark datasets.

Supervised Relation Extraction Between Suicide-Related Entities and Drugs: Development and Usability Study of an Annotated PubMed Corpus.

Drug-induced suicide has been debated as a crucial issue in both clinical and public health research. Published research articles contain valuable data on the drugs associated with suicidal adverse events. An automated process that extracts such information and rapidly detects drugs related to suicide risk is essential but has not been well established. Moreover, few data sets are available for training and validating classification models on drug-induced suicide. This study aimed to build a corpus of drug-suicide relations containing annotated entities for drugs, suicidal adverse events, and their relations. To confirm the effectiveness of the drug-suicide relation corpus, we evaluated the performance of a relation classification model using the corpus in conjunction with various embeddings. We collected the abstracts and titles of research articles associated with drugs and suicide from PubMed and manually annotated them along with their relations at the sentence level (adverse drug events, treatment, suicide means, or miscellaneous). To reduce the manual annotation effort, we preliminarily selected sentences with a pretrained zero-shot classifier or sentences containing only drug and suicide keywords. We trained a relation classification model using various Bidirectional Encoder Representations from Transformer embeddings with the proposed corpus. We then compared the performances of the model with different Bidirectional Encoder Representations from Transformer-based embeddings and selected the most suitable embedding for our corpus. Our corpus comprised 11,894 sentences extracted from the titles and abstracts of the PubMed research articles. Each sentence was annotated with drug and suicide entities and the relationship between these 2 entities (adverse drug events, treatment, means, and miscellaneous). All of the tested relation classification models that were fine-tuned on the corpus accurately detected sentences of suicidal adverse events regardless of their pretrained type and data set properties. To our knowledge, this is the first and most extensive corpus of drug-suicide relations.

:Ausgrabungen in der frühbronzezeitlichen Siedlung im Heraion von Samos 1966

:<i>Ausgrabungen in der frühbronzezeitlichen Siedlung im Heraion von Samos 1966</i>

A Deep Sparse Representation with Random Dictionary for Hyperspectral Image Classification

Hyperspectral image (HSI) classification methods based on deep learning have demonstrated excellent performance, while these deep learning methods take a lot of time to train the parameters. In this paper, we propose a deep sparse representation (SR) network (DSRNet) without spending a lot of time training network parameters in the feature extraction stage. The contributions of this paper are three-fold. First, we introduce random dictionary into HSI classification, and solve sparse representation model under this dictionary. Second, we extend the shallow sparse representation model to the deep sparse representation model, where the SR model needs to be solved for each layer and used to extract the deep features of HSI. Finally, we investigate the classification performance of different classifiers on the deep features extracted by using DSRNet. Experimental results show that the proposed method can achieve better classification results compared with some closely related HSI classification methods and the other state-of-the-art deep learning methods.

Dynamic Modeling Cross-Modal Interactions in Two-Phase Prediction for Entity-Relation Extraction.

Joint extraction of entities and their relations benefits from the close interaction between named entities and their relation information. Therefore, how to effectively model such cross-modal interactions is critical for the final performance. Previous works have used simple methods, such as label-feature concatenation, to perform coarse-grained semantic fusion among cross-modal instances but fail to capture fine-grained correlations over token and label spaces, resulting in insufficient interactions. In this article, we propose a dynamic cross-modal attention network (CMAN) for joint entity and relation extraction. The network is carefully constructed by stacking multiple attention units in depth to dynamic model dense interactions over token-label spaces, in which two basic attention units and a novel two-phase prediction are proposed to explicitly capture fine-grained correlations across different modalities (e.g., token-to-token and label-to-token). Experiment results on the CoNLL04 dataset show that our model obtains state-of-the-art results by achieving 91.72% F1 on entity recognition and 73.46% F1 on relation classification. In the ADE and DREC datasets, our model surpasses existing approaches by more than 2.1% and 2.54% F1 on relation classification. Extensive analyses further confirm the effectiveness of our approach.

Adaptive Prototypical Networks With Label Words and Joint Representation Learning for Few-Shot Relation Classification.

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of entity-relation triple. Although distant supervision methods can effectively alleviate the problem of lack of training data in supervised learning, they also introduce noise into the data and still cannot fundamentally solve the long-tail distribution problem of the training instances. In order to enable the neural network to learn new knowledge through few instances such as humans, this work focuses on few-shot relation classification (FSRC), where a classifier should generalize to new classes that have not been seen in the training set, given only a number of samples for each class. To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes. Second, to more reasonably measure the distances between samples of each category, we introduce a loss function for joint representation learning (JRL) to encode each support instance in an adaptive manner. Extensive experiments have been conducted on FewRel under different few-shot (FS) settings, and the results show that the proposed adaptive prototypical networks with label words and JRL has not only achieved significant improvements in accuracy but also increased the generalization ability of FSRC.

Contribution of labor related gene subtype classification on heterogeneity of polycystic ovary syndrome.

As one of the most common endocrine disorders in women of reproductive age, polycystic ovary syndrome (PCOS) is highly heterogeneous with varied clinical features and diverse gestational complications among individuals. The patients with PCOS have 2-fold higher risk of preterm labor which is associated with substantial infant morbidity and mortality and great socioeconomic cost. The study was designated to identify molecular subtypes and the related hub genes to facilitate the susceptibility assessment of preterm labor in women with PCOS. Four mRNA datasets (GSE84958, GSE5090, GSE43264 and GSE98421) were obtained from Gene Expression Omnibus database. Twenty-eight candidate genes related to preterm labor or labor were yielded from the researches and our unpublished data. Then, we utilized unsupervised clustering to identify molecular subtypes in PCOS based on the expression of above candidate genes. Key modules were generated with weighted gene co-expression network analysis R package, and their hub genes were generated with CytoHubba. The probable biological function and mechanism were explored through Gene Ontology analysis and Kyoto Encyclopedia of Genes and Genomes pathway analysis. In addition, STRING and Cytoscape software were used to identify the protein-protein interaction (PPI) network, and the molecular complex detection (MCODE) was used to identify the hub genes. Then the overlapping hub genes were predicted. Two molecular subtypes were found in women with PCOS based on the expression similarity of preterm labor or labor-related genes, in which two modules were highlighted. The key modules and PPI network have five overlapping five hub genes, two of which, GTF2F2 and MYO6 gene, were further confirmed by the comparison between clustering subgroups according to the expression of hub genes. Distinct PCOS molecular subtypes were identified with preterm labor or labor-related genes, which might uncover the potential mechanism underlying heterogeneity of clinical pregnancy complications in women with PCOS.

Effectiveness of transferring ultrasound deep learning models from adults to pediatrics for frame based pneumonia classification

Hand-held ultrasound devices are emerging as a promising intervention to aid in diagnosing deadly early childhood pneumonia in the developing world. Lung ultrasound (LUS) data, however, can be difficult to read and interpret accurately, and thus require trained professionals. A variety of deep learning (DL) models have been developed to aid professionals in this task, but the difficulty curating quality training datasets limits the generalization capabilities of these models. To combat this data scarcity, we utilized a variety of DL models trained on LUS data collected from adult COVID-19 patients in Italy and were able to apply transfer learning to increase pneumonia related imaging pattern classification in LUS data from children and infants in rural Zambia. In this regard, we found that transfer learning significantly increased frame classification F1 performance as compared to training models from scratch. These findings indicate the promising potential for developing generalizable AI for LUS classification in diverse contexts given limited data. This analysis demonstrates that DL models effectively transfer their capabilities when fine tuned on a new population demographics, allowing the possibility to clinically deploy these models without the need to acquire large amounts of new data.

Transfer Learning for Low-Resource Multilingual Relation Classification

Relation classification (sometimes called relation extraction ) requires trustworthy datasets for fine-tuning large language models, as well as for evaluation. Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English. Despite recent interest in deep generative models for Indian languages, relation classification is still not well served by public datasets. In response, we present IndoRE , a dataset with 21K entity- and relation-tagged gold sentences in three Indian languages (Bengali, Hindi, and Telugu), plus English. We start with a multilingual BERT (mBERT)-based system that captures entity span positions and type information, and provides competitive performance on monolingual relation classification. Using this baseline system, we explore transfer mechanisms between languages and the scope to reduce expensive data annotation while achieving reasonable relation extraction performance. Specifically, we (a) study the accuracy-efficiency trade-off between expensive, manually labeled gold instances vs. automatically translated and aligned silver instances to train a relation extractor, (b) device a simple mechanism for budgeted gold data annotation by intelligently converting distant-supervised silver training instances to gold training instances with human annotators using active learning, and finally (c) propose an ensemble model to provide a performance boost over that achieved via limited gold training instances. We release the dataset for future research. 1

SecureRC: A system for privacy-preserving relation classification using secure multi-party computation

Natural Language Processing (NLP) transforms human language into machine language that can be understood by machines through computer technology. Relation classification is an important semantic extraction task in NLP, which can accurately obtain the semantic relationship between two entities in a text. It has been used extensively in many NLP applications, such as information extraction and question answering. Relation classification can extract accurately relationships between two entities from large amounts of linguistic data. However, collecting such vast amounts of data in relation classification poses serious privacy issues. As far as we know, there is no existing work that implements privacy-preserving relation classification task. In this paper, we consider how to implement privacy-preserving relation classification using attention-based gated recurrent unit (GRU) network. Specifically, we first design three basic privacy-preserving protocols for the non-linear functions (sigmoid and tanh) using secure multi-party computation (MPC). Then, we propose a secure computation protocol SecureGRU for the GRU network based on these three basic protocols. Finally, based on the SecureGRU and the attention mechanism, we obtain the privacy-preserving relation classification system SecureRC. In the semi-honest adversary model, we prove the security of these protocols. Any honest-but-curious adversary is not able to obtain anything beyond what he is allowed to learn. The proposed system is implemented in Python. Experimental results demonstrate the performance of our proposed protocols.

Cost and yield accounting for horticulture, viticulture and nursery

The article deals with the issues of rationalization of cost accounting for production, output and evaluation of horticulture, viticulture and nursery products. A list of cost accounting items is proposed based on their classification in relation to the volume of production, by natural-material form and sources of formation. Recommendations have been developed on the organization of accounting for production costs, valuation of horticulture, viticulture and nursery products at fair value. The method of accounting for potential and actual income and expenses associated with the assessment of horticulture, viticulture and nursery products at fair value is substantiated.

Progress on eco-technology classification in ecologically vulnerable regions of China

Ecological technology is the core of ecological environment governance and restoration in ecologically vulnerable regions. A reasonable classification method is the basis for induction and summary of ecological techno-logy, which is of great significance to classify and solve ecological environmental problems and evaluate the effects of ecological technology implementation. However, there is still no standard method for the classification of ecological technology. From the perspective of ecological technology classification, we summarized the concept of eco-technology and related classification methods, in view of current situation and deficiency of ecological technology related classification, we put forward a system suitable for defining and classifying ecological technology in ecologically vulnerable regions of China, and analyzed the practicality and application prospect. Our review would provide reference for the management and promotion of ecological technology classification.

An angular shrinkage BERT model for few-shot relation extraction with none-of-the-above detection

Few-shot relation extraction aims to solve the problem of insufficient annotated data in relation extraction tasks. Through the comparison between samples, few-shot relation extraction achieves lower-cost relation classification. However, most existing methods only do classification within the scope of enumerated relations. For one of the main challenges faced by the application of few-shot relation extraction-the recognition of the none-of-the-above instances, there has been few works on it. In this paper, we propose an angular shrinkage BERT model for the few-shot relation extraction task with none-of-the-above detection, which uses an additive angular loss to enlarge the margins of different classes in the feature space, and obtain highly discriminative features to improve the recognition ability for none-of-the-above instances. Meanwhile, we present a two-stage training strategy to enhance the stability of the performance. We evaluate our model on the most used few-shot relation extraction dataset FewRel. Experimental results show that our approach outperforms previous sentence-pair methods in scenarios containing none-of-the-above instances, and also achieves improvements on the traditional few-shot relation extraction task compared with our baseline model.

MSRL-Net: A multi-level semantic relation-enhanced learning network for aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) aims to analyze the sentiment polarity of a given text towards several specific aspects. For implementing the ABSA, one way is to convert the original problem into a sentence semantic matching task, using pre-trained language models, such as BERT. However, for such a task, the intra- and inter-semantic relations among input sentence pairs are often not considered. Specifically, the semantic information and guidance of relations revealed in the labels, such as positive, negative and neutral, have not been completely exploited. To address this issue, we introduce a self-supervised sentence pair relation classification task and propose a model named Multi-level Semantic Relation-enhanced Learning Network (MSRL-Net) for ABSA. In MSRL-Net, after recasting the original ABSA task as a sentence semantic matching task, word dependency relations and word-sentence relations are utilized to enhance the word-level semantic representation for the sentence semantic matching task, while sentence semantic relations and sentence pairs relations are utilized to enhance the sentence-level semantic representation for sentence pair relation classification. Empirical experiments on SemEval 2014 Task 4, SemEval 2016 Task 5 and SentiHood show that MSRL-Net significantly outperforms other baselines such as BERT in terms of accuracy, Macro-F1 and AUC.