Relation Classification Research Articles

Exploring ResNet-18 Estimation Design through Multiple Implementation Iterations and Techniques in Legacy Databases

In a rapidly evolving landscape where automated systems and database applications are increasingly crucial, there is a pressing need for precise and efficient object recognition methods. This study contributes to this burgeoning field by examining the ResNet-18 architecture, a proven deep learning model, in the context of fruit image classification. The research employs an elaborate experimental setup featuring a diverse fruit dataset that includes Rambutan, Mango, Santol, Mangosteen, and Guava. The efficacy of single versus multiple ResNet-18 models is compared, shedding light on their relative classification accuracy. A unique aspect of this study is the establishment of a 90% decision threshold, introduced to mitigate the risk of incorrect classification. Our statistical analysis reveals a significant performance advantage of multiple ResNet-18 models over single models, with an average improvement margin of 15%. This finding substantiates the study’s central hypothesis. The implemented 90% decision threshold is determined to play a pivotal role in augmenting the system’s overall accuracy by minimizing false positives. However, it’s worth noting that the increased computational complexity associated with deploying multiple models necessitates further scrutiny. In sum, this study provides a nuanced evaluation of single and multiple ResNet-18 models in the realm of fruit image classification, emphasizing their utility in practical, real-world applications. The research opens avenues for future exploration by refining these methodologies and investigating their applicability to broader object recognition tasks.

Multi-transformer based on prototypical enhancement network for few-shot relation classification with domain adaptation

Few-shot relation classification aims to predict the relation between entity pairs in unseen sentences with a few labeled sentences. In real-world scenarios, the target domains often have limited data and could differ significantly from the source domains. Existing studies focus on the representation of entity pairs, ignoring the relation between the sentences and the entity pairs. Some researchers use feature-adaptive methods that do not consider that features contribute differently to relation classification. To solve these challenges, a multi-transformer based on a prototypical enhancement network (MTPEnet) is presented for few-shot relation classification with domain adaptation in this study. Specifically, for MTPEnet, two main parts are conducted. First, in the calculation of the prototype, a local and global representations (LGR) module is established to improve the representation of sentences. LGR considers not only the head and tail entities in a sentence but also the relation between the entity pair and the entire sentence. Second, a multi-transformer (MT) feature transformation module is introduced to address the cross-domain problem. Different weights are assigned to the target domain features according to the degree of fusion between the features in the target and source domains. Finally, the experimental results on the datasets FewRel 2.0 and FewTAC demonstrate the superiority of MTPEnet over several baseline models.

Calibrating variant curation by clinical context based on factors that influence patients’ tolerance of uncertainty

PurposeShared decision making manages genomic uncertainty by integrating molecular and clinical uncertainties with patient values to craft a person-centered management plan. Laboratories seek genomic report consistency, agnostic to clinical context. Molecular reports often mask laboratory-managed uncertainties from clinical decision making. Better integration of these uncertainty management strategies requires a nuanced understanding of patients’ perceptions and reactions to test uncertainties. We explored patients’ tolerance to variant uncertainty in 3 parameters: (1) relative causal significance, (2) risk accuracy, and (3) classification validity. MethodDeliberative forums were undertaken with 18 patients with predictive testing experience. Uncertainty deliberations were elicited for each parameter. A thematic framework was first developed, and then mapped to whether they justified tolerance to more or less parameter-specific uncertainty. ResultsSix identified themes mapped to clinical and personal domains. These domains generated opposing forces when calibrating uncertainty. Personal themes justified tolerance of higher uncertainty and clinical themes lower uncertainty. Decision making in uncertainty focused on reducing management regret. Open communication increased tolerance of classification validity and risk accuracy uncertainty. Using these data, we have developed a nascent clinical algorithm integrating molecular uncertainty with clinical context through a targeted communication framework. ConclusionMaximizing test utility necessitates context-specific recalibration of uncertainty management and communication.

Point estimation and related classification problems for several Lindley populations with application using COVID-19 data

ABSTRACT The problems of point estimation and classification under the assumption that the training data follow a Lindley distribution are considered. Bayes estimators are derived for the parameter of the Lindley distribution applying the Markov chain Monte Carlo (MCMC), and Tierney and Kadane's [Tierney and Kadane, Accurate approximations for posterior moments and marginal densities, J. Amer. Statist. Assoc. 81 (1986), pp. 82–86] methods. In the sequel, we prove that the Bayes estimators using Tierney and Kadane's approximation and Lindley's approximation both converge to the maximum likelihood estimator (MLE), as n → ∞ , where n is the sample size. The performances of all the proposed estimators are compared with some of the existing ones using bias and mean squared error (MSE), numerically. It has been noticed from our simulation study that the proposed estimators perform better than some of the existing ones. Applying these estimators, we construct several plug-in type classification rules and a rule that uses the likelihood accordance function. The performances of each of the rules are numerically evaluated using the expected probability of misclassification (EPM). Two real-life examples related to COVID-19 disease are considered for illustrative purposes.

Noun Compound Interpretation With Relation Classification and Paraphrasing

Noun compounds are abundant in various languages and their interpretations have been applied in a wide range of NLP tasks. However, most existing work only uses relation classification- or paraphrasing-based methods to model this problem, failing in coverage or accuracy. We argue that the above two approaches are complementary to each other for the noun compound interpretation. In this paper, we propose a two-phase strategy to solve this task. The first phase is to perform the relation classification sub-task with a novel multi-view representation learning model. When noun compounds are predicted as the non-semantic relation, i.e., NA, or the confidence scores are below the threshold, the second phase, namely paraphrasing, will be triggered to interpret noun compounds with a contrastive slot filling method. To evaluate the effectiveness of our methods, we construct the largest Chinese dataset for noun compound interpretation in the life service domain. The experimental results on our constructed and public datasets prove the effectiveness of our solution. Furthermore, the online A/B testing on Meituan APP suggests that the Query View Click-Through Rate increases by 0.91% when noun compounds are used to enrich semantic information of items with the help of their interpretations on the platform.

Towards Hard Few-Shot Relation Classification

Few-shot relation classification (FSRC) focuses on recognizing novel relations by learning with merely a handful of annotated instances. Meta-learning has been widely adopted for such a task, which trains on randomly generated few-shot tasks to learn generic data representations. Despite impressive results achieved, existing models still perform suboptimally when handling hard FSRC tasks with similar categories that confuse the model to distinguish correctly. We argue this is largely due to two reasons, 1) ignoring pivotal and discriminate information that is crucial to distinguish confusing classes, and 2) training indiscriminately via randomly sampled tasks of varying difficulty. In this paper, we introduce a novel prototypical network approach with contrastive learning that learns more informative and discriminative representations by exploiting relation label information. We further design two strategies that increase the difficulty of training tasks and allow the model to adaptively learn to focus on hard tasks. By doing so, our model can better represent subtle inter-relation variance and grow up through task difficulty. Extensive experiments on three standard benchmarks demonstrate the effectiveness of our method.

Transfer Learning across Graph Convolutional Networks: Methods, Theory, and Applications

Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data. Existing models were designed for the nodes on a single graph, which would not be able to utilize information across multiple graphs. The real world does have multiple graphs where the nodes are often partially aligned . For examples, knowledge graphs share a number of named entities though they may have different relation schema; collaboration networks on publications and awarded projects share some researcher nodes who are authors and investigators, respectively; people use multiple web services, shopping, tweeting, rating movies, and some may register the same email account across the platforms. In this paper, we propose partially aligned graph convolutional networks to learn node representations across the models. We provide multiple methods such as model sharing, regularization, and alignment reconstruction, as well as theoretical analysis to positively transfer knowledge across the set of partially aligned nodes. Extensive experiments on real-world knowledge graphs, collaboration networks, and bipartite rating graphs show the superior performance of our proposed methods on relation classification, link prediction, and item recommendation.

The harpoon stands yonder: Shape variation and functional constraints in Mesolithic complex weapon points from the circum-Baltic Sea area

Mesolithic harpoons are structurally complex weapon points and significant sources of archaeological information. Nonetheless, separating different types of information inherent in harpoon point shapes (e.g., aspects relating to mechanical performance, personal or group craft variation and chronology) using descriptive approaches is difficult. In this study, we employed an exploratory geometric morphometric approach to the analysis of 28 Mesolithic harpoon points, and 144 undated harpoon points from the circum-Baltic Sea area in order to retrieve both functional and spatiotemporal information. By analyzing harpoon structure statistically through (i.) a shape proxy (harpoon silhouette) and (ii.) harpoon sub-structures (barbs), we have been able to reveal information related to both variation in shape convention and functional constraints. Barb shape results revealed statistically significant chronological and geographical groupings with spatiotemporal barb-shape trajectories made visible and objective evaluation of how barb-shape conventions impacted functional variation. In addition, harpoon silhouette shape distributions were shown to have potential as sources for robust artifact classifications in relation to functional constraints and raw-material engagement. These results suggest that morphometric approaches similar to the ones we have employed offer promising ways of addressing specific archaeological questions in the context of harpoon point shapes and, more generally, other complex weapon point forms.

Action class relation detection and classification across multiple video datasets

The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations enable dataset augmentation, it is only applicable to those covered by MetaVD. For an external dataset to enjoy the same benefit, the relations between its action classes and those in MetaVD need to be determined. To address this issue, we consider two new machine learning tasks: action class relation detection and classification. We propose a unified model to predict relations between action classes, using language and visual information associated with classes. Experimental results show that (i) pre-trained recent neural network models for texts and videos contribute to high predictive performance, (ii) the relation prediction based on action label texts is more accurate than based on videos, and (iii) a blending approach that combines predictions by both modalities can further improve the predictive performance in some cases.

Relation Extraction Based on Prompt Information and Feature Reuse

ABSTRACT To alleviate the problem of under-utilization features of sentence-level relation extraction, which leads to insufficient performance of the pre-trained language model and underutilization of the feature vector, a sentence-level relation extraction method based on adding prompt information and feature reuse is proposed. At first, in addition to the pair of nominals and sentence information, a piece of prompt information is added, and the overall feature information consists of sentence information, entity pair information, and prompt information, and then the features are encoded by the pre-trained language model ROBERTA. Moreover, in the pre-trained language model, BIGRU is also introduced in the composition of the neural network to extract information, and the feature information is passed through the neural network to form several sets of feature vectors. After that, these feature vectors are reused in different combinations to form multiple outputs, and the outputs are aggregated using ensemble-learning soft voting to perform relation classification. In addition to this, the sum of cross-entropy, KL divergence, and negative log-likelihood loss is used as the final loss function in this paper. In the comparison experiments, the model based on adding prompt information and feature reuse achieved higher results of the SemEval-2010 task 8 relational dataset.

Advanced Fuzzy Sets and Genetic Algorithm Optimizer for Mammographic Image Enhancement

A well-researched field is the development of Computer Aided Diagnosis (CADx) Systems for the benign-malignant classification of abnormalities detected by mammography. Due to the nature of the breast parenchyma, there are significant uncertainties about the shape and geometry of the abnormalities that may lead to an inaccurate diagnosis. These same uncertainties give mammograms a fuzzy character that is essential to the application of fuzzy processing. Fuzzy set theory considers uncertainty in the form of a membership function, and therefore fuzzy sets can process imperfect data if this imperfection originates from vagueness and ambiguity rather than randomness. Fuzzy contrast enhancement can improve edge detection and, by extension, the quality of related classification features. In this paper, classical (Linguistic hedges and fuzzy enhancement functions), advanced fuzzy sets (Intuitionistic fuzzy set (ΙFS), Pythagorean fuzzy set (PFS), and Fermatean fuzzy sets (FFS)), and a Genetic Algorithm optimizer are proposed to enhance the contrast of mammographic features. The advanced fuzzy sets provide better information on the uncertainty of the membership function. As a result, the intuitionistic method had the best overall performance, but most of the techniques could be used efficiently, depending on the problem that needed to be solved. Linguistic methods could provide a more manageable way of spreading the histogram, revealing more extreme values than the conventional methods. A fusion technique of the enhanced mammography images with Ordered Weighted Average operators (OWA) achieves a good-quality final image.

Phytosociology of the Herbaceous Flora of University of Ibadan Oil Palm Plantation, University of Ibadan, Ibadan, Southwest, Nigeria

Plantation agriculture perturbs native flora of ecosystems. This impacts vegetation biodiversity, through species invasion and shift in weeds population dynamics. Oil palm plantations are common in tropical landscapes, and can cause long-term floristic changes. There is paucity of knowledge on inventory and potential impacts of the plantation on community structure of plants. This study investigated herbaceous flora diversity and phytosociology as indicators of appropriateness of management strategy in the University of Ibadan oil palm plantation. The study site is located in a lowland rainforest at the Teaching and Research Farm, University of Ibadan, Ibadan, Nigeria on 07°27`253`N latitude and longitude 03°53`427`E. A systematic sampling was employed to enumerate herbaceous flora of a hectare mega plot. The hectare was laid along 100 m transects at 10 m intervals, with 10 m separating each transect. Each transect was laid to cut across middle of 9 m x 9 m x 9 m plant spacing for oil palm. Data were collected on species composition, frequency and density for determination of relative importance value (RIV), species diversity, ordination and classification. The plantation consisted of 32 herbaceous species in 15 plant families. Commelina erecta had the highest RIV (12.621) while Alchornea cordifolia had the least (RIV=0.288). Diversity indices indicated high species richness (Simpson Index = 0.909) among enumerated species and species co-dominance (D = 0.091) Ordination biplots indicated three distinct vegetation structures (Secondary, wetland, dryland/fallow). Classification model showed Commelina erecta had widest coverage of 92% in distribution at the site followed by Commelina benghalensis at 88%. The Oil palm plantation is heterogeneous in species composition, and was not detrimentally invaded. Weeding regimes and other agronomic practices in the plantation should be ecologically integrated to conserve its native vegetation.

Fine-tuning language models to recognize semantic relations

Transformer-based pre-trained Language Models (PLMs) have emerged as the foundations for the current state-of-the-art algorithms in most natural language processing tasks, in particular when applied to context rich data such as sentences or paragraphs. However, their impact on the tasks defined in terms of abstract individual word properties, not necessary tied to their specific use in a particular sentence, has been inadequately explored, which is a notable research gap. Addressing this gap is crucial for advancing our understanding of natural language processing. To fill this void, we concentrate on classification of semantic relations: given a pair of concepts (words or word sequences) the aim is to identify the semantic label to describe their relationship. E.g. in the case of the pair green/colour, “is a” is a suitable relation while “part of”, “property of”, and “opposite of” are not suitable. This classification is independent of a particular sentence in which these concepts might have been used. We are first to incorporate a language model into both existing approaches to this task, namely path-based and distribution-based methods. Our transformer-based approaches exhibit significant improvements over the state-of-the-art and come remarkably close to achieving human-level performance on rigorous benchmarks. We are also first to provide evidence that the standard datasets over-state the performance due to the effect of “lexical memorisation.” We reduce this effect by applying lexical separation. On the new benchmark datasets, the algorithmic performance remains significantly below human-level, highlighting that the task of semantic relation classification is still unresolved, particularly for language models of the sizes commonly used at the time of our study. We also identify additional challenges that PLM-based approaches face and conduct extensive ablation studies and other experiments to investigate the sensitivity of our findings to specific modelling and implementation choices. Furthermore, we examine the specific relations that pose greater challenges and discuss the trade-offs between accuracy and processing time.

SPBERE: Boosting span-based pipeline biomedical entity and relation extraction via entity information

Triplet extraction is one of the fundamental tasks in biomedical text mining. Compared with traditional pipeline approaches, joint methods can alleviate the error propagation problem from entity recognition to relation classification. However, existing methods face challenges in detecting overlapping entities and overlapping relations, which are ubiquitous in biomedical texts. In this work, we propose a novel pipeline method of end-to-end biomedical triplet extraction. In particular, a span-based detection strategy is used to detect the overlapping triplets by enumerating possible candidate spans and entity pairs. The strategy is further used to capture different contextualized representations via an entity model and a relation model, respectively. Furthermore, to enhance interrelation between spans, entity information from the output of the entity model is used to construct the input for the relation model without utilizing any external knowledge. Our approach is evaluated on the drug–drug interaction (DDI) and chemical-protein interaction (CHEMPROT) datasets, exhibiting improvement of the absolute F1-score in relation extraction by 3.5%–3.7% compared prior work. The experimental results highlight the importance of overlapping triplet detection using the span-based approach, acquisition of various contextualized representations via different in-domain pre-trained language models, and early fusion of entity information in the relation model.

FREDA: Few-Shot Relation Extraction Based on Data Augmentation

The primary task of few-shot relation extraction is to quickly learn the features of relation classes from a few labelled instances and predict the semantic relations between entity pairs in new instances. Most existing few-shot relation extraction methods do not fully utilize the relation information features in sentences, resulting in difficulties in improving the performance of relation classification. Some researchers have attempted to incorporate external information, but the results have been unsatisfactory when applied to different domains. In this paper, we propose a method that utilizes triple information for data augmentation, which can alleviate the issue of insufficient instances and possesses strong domain adaptation capabilities. Firstly, we extract relation and entity pairs from the instances in the support set, forming relation triple information. Next, the sentence information and relation triple information are encoded using the same sentence encoder. Then, we construct an interactive attention module to enable the query set instances to interact separately with the support set instances and relation triple instances. The module pays greater attention to highly interactive parts between instances and assigns them higher weights. Finally, we merge the interacted support set representation and relation triple representation. To our knowledge, we are the first to propose a method that utilizes triple information for data augmentation in relation extraction. In our experiments on the standard datasets FewRel1.0 and FewRel2.0 (domain adaptation), we observed substantial improvements without including external information.

Hybrid Enhancement-based prototypical networks for few-shot relation classification

Hybrid Enhancement-based prototypical networks for few-shot relation classification

Evaluation of Performance Metrics in Heart Disease by Machine Learning Techniques

Aim: In addition to affecting the individual sociologically and psychologically, heart disease also poses important problems in health systems. Evaluation of heart disease performances has gained great importance in terms of machine learning method. In the study, performances were compared with the machine learning method for risk methods that classify heart illness.
 Materials and Methods: The categorization process Throughout the research made use of the "Heart Disease Dataset," an open access dataset. F1-score, sensitivity, selectivity, accuracy, balanced accuracy, negative and positive predictive values were used to assess the performance of the categorisation model using the machine learning approach. Random forest method, one of the variable selection methods, was used.
 Results: According to the relational classification model's classification findings for heart disease, the accuracy, balanced accuracy, sensitivity, selectivity, positive predictive value, negative predictive value, and F1-score values were observed to be 0.997, 0.997, 0.995, 1, 1, and 0.995, respectively. 
 Conclusion: The relational classification model proposed in the analysis obtained in the web-based open access dataset yielded distinctively successful results in classifying heart disease according to performance criteria.

Introducing the Concept ‘Intra-Local Governmental Relations’ for Proper and Future Usage in Public Administration Research and Education: A Possible Case for Bathos

Usage of the phrase ‘conceptual bathos’ in this paper is simply to engender curiosity of the readership but above that, it is used to caution emerging researchers [especially in the field of public administration] against overlooking or demeaning important subjects or concepts to simple or ordinary ones. Specifically, the paper refers to ‘Intra-local governmental relations’ as a concept that has suffered the same cause of negation to argue for its proper usage in future. This concept is found within the orbit of intergovernmental relations (IGR) and is a term of reference for various internal municipality relations. However, it is suspected that because of the inherent similarities and motherhood relationship between IGR and ILGR researchers have failed to draw differences thereby causing confusion. The extent of this confusion may lead to a suggestion that these concepts are inseparable and therefore can be used to explain each one’s context. The current paper characterises such acts as tangential and generalist conceptual approach which is often not aware of the important groupings (classifications) of governmental relations. By collecting and unpacking data from the existing research outputs, books, journal articles and government publications, the current paper finally realised its objective, which was to re-introduce ILGR into the academic discourse and the anticipation is that emerging Public Administration researchers and scholars will use the concept properly and correctly.

Transfer function approaches for SEEG brain electrode interface applied to tissue classification

This paper is about transfer function approaches for brain-electrode interface modelling in the context of StereoElectroEncephaloGraphy, and their possible use in tissue classification (between grey and white matter). Monopolar and bipolar configurations are first reviewed, giving rise to possible nonparametric and parametric identification methods, as well as related possible classification results (for identical tissues and distinct tissues at measurement points, respectively). A method combining both approaches is then proposed, so as to end up with a classification at each measurement point in any case. The proposed methodology is implemented with clinical data collected from a set of epileptic patients, confirming its interest by providing more than 70% of accuracy in the obtained results.

An Easy Partition Approach for Joint Entity and Relation Extraction

The triplet extraction (TE) task aims to identify the entities and relations mentioned in a given text. TE consists of two tasks: named entity recognition (NER) and relation classification (RC). Previous work has either treated TE as two separate tasks with independent encoders, or as a single task with a unified encoder. However, both approaches have limitations in capturing the interaction and independence of the features for different subtasks. In this paper, we propose a simple and direct feature selection and interaction scheme. Specifically, we use a pretraining language model (e.g., BERT) to extract various features, including entity recognition, shared, and relation classification features. To capture the interaction, shared features consist of the common semantic information used by the two tasks simultaneously. We use a gate module to obtain the task-specific features. Experimental results on various public benchmarks show that our proposed method can achieve competitive performance, and the calculation speed of our model is seven times faster than CasRel, and two times faster than PFN.