Semantic Associations Research Articles

Modeling verbal short-term memory: A walk around the neighborhood.

When remembering over the short-term, long-term knowledge has a large effect on the number of correctly recalled items and little impact on memory for order. This is true, for example, when the effects of semantic category are examined. Contrary to what these findings suggest, Poirier et al. in 2015 proposed that memory for order relies on the level of activation within long-term networks. Importantly, although their view has been criticized, they showed that manipulating semantic associations led to item migrations that were atypical. In this article, we show that similar migrations can be obtained with another knowledge-based factor: orthographic neighborhood. In three experiments, we manipulated the orthographic neighborhood of to-be-recalled items. The latter is a sublexical factor; as such, it is much less likely than semantic relatedness to involve demand characteristics or grouping strategies. The first experiment established that the neighborhood manipulation produced the pattern of item migrations previously observed with semantic relatedness, confirming that the migration effect can generalize to other variables. The last two experiments suggested that migrations were due to the features shared across list items rather than to item co-activation (as in Poirier et al.). The results were successfully modeled by calling upon the Revised Feature Model, where recall depends on selecting a retrieval candidate based on the features of the cueing information. Overall, our findings underline the usefulness of a model where retrieval is determined by relative distinctiveness and underline that multiple mechanisms can lead to order errors in recall. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Screening potential lncRNA biomarkers for breast cancer and colorectal cancer combining random walk and logistic matrix factorization.

Breast cancer and colorectal cancer are two of the most common malignant tumors worldwide. They cause the leading causes of cancer mortality. Many researches have demonstrated that long noncoding RNAs (lncRNAs) have close linkages with the occurrence and development of the two cancers. Therefore, it is essential to design an effective way to identify potential lncRNA biomarkers for them. In this study, we developed a computational method (LDA-RWLMF) by integrating random walk with restart and Logistic Matrix Factorization to investigate the roles of lncRNA biomarkers in the prognosis and diagnosis of the two cancers. We first fuse disease semantic and Gaussian association profile similarities and lncRNA functional and Gaussian association profile similarities. Second, we design a negative selection algorithm to extract negative LncRNA-Disease Associations (LDA) based on random walk. Third, we develop a logistic matrix factorization model to predict possible LDAs. We compare our proposed LDA-RWLMF method with four classical LDA prediction methods, that is, LNCSIM1, LNCSIM2, ILNCSIM, and IDSSIM. The results from 5-fold cross validation on the MNDR dataset show that LDA-RWLMF computes the best AUC value of 0.9312, outperforming the above four LDA prediction methods. Finally, we rank all lncRNA biomarkers for the two cancers after determining the performance of LDA-RWLMF, respectively. We find that 48 and 50 lncRNAs have the highest association scores with breast cancer and colorectal cancer among all lncRNAs known to associate with them on the MNDR dataset, respectively. We predict that lncRNAs HULC and HAR1A could be separately potential biomarkers for breast cancer and colorectal cancer and need to biomedical experimental validation.

DGTR: Dynamic graph transformer for rumor detection.

Social media rumors have the capacity to harm the public perception and the social progress. The news propagation pattern is a key clue for detecting rumors. Existing propagation-based rumor detection methods represent propagation patterns as a static graph structure. They simply consider the structure information of news distribution in social networks and disregard the temporal information. The dynamic graph is an effective modeling tool for both the structural and temporal information involved in the process of news dissemination. Existing dynamic graph representation learning approaches struggle to capture the long-range dependence of the structure and temporal sequence as well as the rich semantic association between full graph features and individual parts. We build a transformer-based dynamic graph representation learning approach for rumor identification DGTR to address the aforementioned challenges. We design a position embedding format for the graph data such that the original transformer model can be utilized for learning dynamic graph representations. The model can describe the structural long-range reliance between the dynamic graph nodes and the temporal long-range dependence between the temporal snapshots by employing a self-attention mechanism. In addition, the CLS token in transformer may model the rich semantic relationships between the complete graph and each subpart. Extensive experiments demonstrate the superiority of our model when compared to the state of the art.

Hierarchical Sliding Inference Generator for Question-driven Abstractive Answer Summarization

Text summarization on non-factoid question answering (NQA) aims at identifying the core information of redundant answer guidance using questions, which can dramatically improve answer readability and comprehensibility. Most existing approaches focus on extracting query-related sentences to construct a summary, where the logical connection of natural language and the hierarchical interpretable semantic association are often neglected, thus degrading performance. To address these issues, we propose a novel question-driven abstractive answer summarization model, called the H ierarchical S liding I nference G enerator (HSIG), to form inferable and interpretable summaries by explicitly introducing hierarchical information reasoning between questions and corresponding answers. Specifically, we first apply an elaborately designed hierarchical sliding fusion inference model to determine the most relevant question sentence-level representation that provides a deeper interpretable basis for sentence selection in summarization, which further increases computational performance on the premise of following the semantic inheritance structure. Additionally, to improve summary fluency, we construct a double-driven selective generator to integrate various semantic information from two mutual question-and-answer perspectives. Experimental results illustrate that compared with state-of-the-art baselines, our model achieves remarkable improvement on two benchmark datasets and specifically improves the 2.46 ROUGE-1 points on PubMedQA, which demonstrates the superiority of our model on abstractive summarization with hierarchical sequential reasoning.

Perceived differences in peer-to-peer accommodation before and after COVID-19: evidence from China

PurposeBased on text content analysis using big data, this study aims to explore differences in guest perceptions of peer-to-peer accommodations before and after COVID-19 to provide suggestions for the development of these properties in China postpandemic.Design/methodology/approachA guest perception dictionary was established by collecting Ctrip customer reviews of peer-to-peer accommodations. After data cleaning, thematic word analysis and semantic association network analysis were used to explore perceptions and thematic differences before and after COVID-19.FindingsThis research constructed a multidimensional framework of guest-perceived values for peer-to-peer accommodation in the context of COVID-19. The findings showed that the emphasis on functionality in peer-to-peer accommodation changed; perceived emotional values associated with peer-to-peer stays were more complex; perceived social values decreased, host–guest interactions were reduced and online communication became a stronger trend; tourist preferences for types of experiences changed, and people changed their destination selections; perceived conditional value was reflected in perceived risks, and the perceptions of environmental health, service and physical risks increased.Research limitations/implicationsThis research has constructed a multidimensional framework of tourist perceived value on the basis of peer-to-peer accommodation context and epidemic background and has thus shown the changes in tourist perceived value of peer-to-peer accommodation before and after COVID-19.Originality/valueTo the best of authors’ knowledge, this research constitutes the first attempt to explore the perceptual differences for peer-to-peer accommodations before and after COVID-19 based on an extensive data set of online reviews from multiple provinces of China.

Learning Spatial-Temporal Dynamics for Short-Term Passenger Flow Prediction in Urban Rail Transit

Accurate short-term passenger flow prediction in urban rail transit (URT) plays an important role in ensuring the stable operation of the URT systems. Because of the complex dynamic spatial-temporal dependencies and potential semantic correlations of the URT network, accurate and effective short-term passenger flow prediction is challenging. To solve these problems, a novel model called the dynamic spatial-temporal graph convolutional network (DSTGCN) was proposed. Firstly, spatial semantic graphs (SSGs) were established to encode the spatial dependencies and semantic correlations of the URT network. Meanwhile, the dynamic graph convolutional network (DGCN) with the spatial attention mechanism was used to learn the dynamic spatial correlations of the nodes in the SSGs. Then, the long short-term memory (LSTM) network was integrated into the DGCN to learn the dynamic changes of passenger flow and capture local temporal dependencies. Moreover, the temporal attention mechanism was introduced after LSTM to capture global dynamic temporal correlations by adjusting the weights of different sequence information. Finally, the full connection layers were used to output the prediction results. Several experiments were conducted on Nanning Metro Line 1 real datasets to evaluate the model. The experimental results showed that the DSTGCN can effectively capture the dynamic spatial-temporal dependencies and semantic associations of the passenger flow. Besides, the prediction performances of the DSTGCN were better than those of existing baseline models, and it can provide technical support for improving the intelligent planning and operation decisions of URT systems.

AABLSTM: A Novel Multi-task Based CNN-RNN Deep Model for Fashion Analysis

With the rapid growth of online commerce and fashion-related applications, visual clothing analysis and recognition has become a hotspot in computer vision. In this paper, we propose a novel AABLSTM network, which is based on deep CNN-RNN, to solve the visual fashion analysis of clothing category classification, attribute detection, and landmark localization. The designed fashion model is leveraged with the multi-task driven mechanism as follows: firstly, a bidirectional LSTM (Bi-LSTM) branch is proposed for efficiently mining the semantic association between related attributes so as to improve the precision of clothing category classification and attribute detection; then, an imitated hourglass sub-network of “down-up sampling” is constructed for boosting the accuracy of fashion landmark localization; and finally, a specially designed multi-loss function is constructed to better optimize the network training. Extensive experimental results on large-scale fashion datasets demonstrate the superior performance of our approach.

Semantic Representations With Attention Networks for Boosting Image Captioning

Image captioning has shown encouraging outcomes with Transformer-based architectures that typically use attention-based methods to establish semantic associations between objects in an image for caption prediction. Nevertheless, when appearance features of objects in an image display low interdependence, attention-based methods have difficulty in capturing the semantic association between them. To tackle this problem, additional knowledge beyond the task-specific dataset is often required to create captions that are more precise and meaningful. In this article, a semantic attention network is proposed to incorporate general-purpose knowledge into a transformer attention block model. This design combines visual and semantic properties of internal image knowledge in one place for fusion, serving as a reference point to aid in the learning of alignments between vision and language and to improve visual attention and semantic association. The proposed framework is validated on the Microsoft COCO dataset, and experimental results demonstrate competitive performance against the current state of the art.

Fuzzy Rule-Based Model to Train Videos in Video Surveillance System

With the proliferation of the internet, big data continues to grow exponentially, and video has become the largest source. Video big data introduces many technological challenges, including compression, storage, transmission, analysis, and recognition. The increase in the number of multimedia resources has brought an urgent need to develop intelligent methods to organize and process them. The integration between Semantic link Networks and multimedia resources provides a new prospect for organizing them with their semantics. The tags and surrounding texts of multimedia resources are used to measure their semantic association. Two evaluation methods including clustering and retrieval are performed to measure the semantic relatedness between images accurately and robustly. A Fuzzy Rule-Based Model for Semantic Content Extraction is designed which performs classification with fuzzy rules. The features extracted are trained with the neural network where each network contains several layers among them each layer of neurons is dedicated to measuring the weight towards different semantic events. Each neuron measures its weight according to different features like shape, size, direction, speed, and other features. The object is identified by subtracting the background features and trained to detect based on the features like size, shape, and direction. The weight measurement is performed according to the fuzzy rules and based on the weight measures. These frameworks enhance the video analytics feature and help in video surveillance systems with better accuracy and precision.

GE-Blender: Graph Based Knowledge Enhancement for Blender

In spite of the considerable accomplishments in open-domain dialogue generation, the presence of unseen entities can substantially impact the task, resulting in a performance decline in model-driven dialogue generation. While previous research has utilized retrieved knowledge of seen entities to augment model representation, a comprehensive exploration of unseen entities, including their potential co-occurrence and semantic associations within the entity category, remains largely uncharted. In this study, we propose an approach to address this challenge. We construct a graph by extracting entity nodes, enhancing the contextual representation of unseen entities by leveraging the 1-hop surrounding nodes of associated entities. Furthermore, we introduce a named entity tag prediction task to address the issue of unseen entities not present in the constructed graph. We conduct our experiments on an open dataset Wizard of Wikipedia and the empirical results indicate that our approach outperforms the state-of-the-art approaches on Wizard of Wikipedia.

“Greece” semantic field in Marina Tsvetaeva’s idiolect

The presentation of an author’s individual linguistic picture of the world by describing the structure and content of semantic fields is one of the relevant areas of literary texts’ and author idiolects’ analysis in modern linguistics. The article is devoted to the semantic and associative analysis of the lexemes comprising the “Greece” semantic field in Marina Tsvetaeva’s idiolect. The analysis enables to state the correlations between the “Greece” and other key semantic fields and to identify universal and the author’s individual semantic meanings and associations of the lexemes, which form the core and periphery of the semantic field “Greece”. The latter aspect of the analysis has not come into the linguistic research focus yet. The analysis of semantic fields is especially effective in the study of Marina Tsvetaeva’s idiolect, which is characterized by semantic compression, dynamism in the unfolding of meanings and semantic capacity of words. The core of the semantic field under study is the lexeme Greece, the center of the field includes the one-root words Greek, a Greek, the synonym Hellas, as well as its derivatives. The periphery of the field consists of toponyms, names of garments, numerous ancient anthroponyms and theonyms. The lexemes of the semantic field “Greece” also represent other significant semantic fields in Marina Tsvetaeva’s poetic, prose and epistolary texts. They denote the following meanings and associations: ‘culture’, ‘education’, ‘creativity’, ‘love for freedom’, ‘Orthodox faith’, ‘kindness, generosity’. The semantic field “Greece” is mainly associated with people dear to the poetess: her father Ivan Tsvetaev, Maximilian Voloshin, Rainer Maria Rilke. Recreating the spirit and culture of Greece, Tsvetaeva embodied the image of an era close to her, a country native to her in spirit and in which she did not have to be disappointed.

Loop Residual Attention Network for Automatic Segmentation of COVID-19 Chest X-Ray Images

As COVID-19 continues to put pressure on the global healthcare industry, using artificial intelligence to analyze chest X-rays (CXR) has become an effective way to diagnose the virus and treat patients. Despite that many studies have made significant progress in COVID-19 detection, accurately segmenting infected regions with variable locations and scales from COVID-19 CXR remains challenging. Therefore, this paper proposes a novel framework for COVID-19 CXR image segmentation. Specifically, we design a loop residual module to cyclically extract feature information in the process of encoding and decoding splicing, avoiding the loss of complex semantic information in network computing. At the same time, an absolute position information coding block is proposed to strengthen the position information of feature pixels. Moreover, a hybrid attention module is designed to establish semantic associations between channels and multi-scale spaces. Better feature representation is formed by the fusion of location and scale information to alleviate the impact of variable infection regions on segmentation performance. Extensive experiments are conducted on the public COVID-19 CXR dataset COVID-Qu-Ex, and the results show that our network is leading and robust compared to other networks in COVID-19 segmentation.

Mining Sematic Association Rules from RDF Data

Many fields rely heavily on the accurate and consistent portrayal of structured data. In order to effectively express and link information on the Semantic Web, RDF (Resource Description Framework) data is essential. Here, we present a process for extracting semantic association rules from RDF data. For our method, we employ the Apriori algorithm to mine the RDF triples for hidden connections between ideas and relationships. Using metrics such as confidence, support, and lift, we examine how well our model performs. We also give visual representations, like as scatter plots and clustered matrices, to make the correlations easier to understand and analyse. The findings validate our model's potential to unearth significant relationships, which in turn reveal important details about the RDF data's underlying semantics. Our findings are discussed, and suggestions for further study are provided.

Optimal Recommendation Models Based on Knowledge Representation Learning and Graph Attention Networks

Knowledge representation learning techniques process the knowledge graph, embedding entities and relationships into a continuous dense low-dimensional vector space, and providing the rich semantic association information between entities embedded in the knowledge graph to the recommendation module, improving recommendation performance and providing better interpretability. However, the knowledge representation learning techniques based on the translation model TransD with too many parameters and no association between entity representations are difficult to apply to large knowledge graph, as well as the problem is that most existing knowledge graph which based on recommendation systems ignore the different levels of importance that users attach to different relationships of items. To address these shortcomings, we propose an improved knowledge representation learning model Cluster TransD and a recommendation model Cluster TransD-GAT based on knowledge graph and graph attention networks, where the Cluster TransD model reduces the number of entity projections, makes the association between entity representations, reduces the computational pressure, and makes it better to be applied to the large knowledge graph, and the Cluster TransD-GAT model can capture the attention of different users to different relationships of items. Extensive comparison and ablation experiments on three real datasets show that the model proposed in this paper has significant performance improvements in terms of average ranking, accuracy and recall of the scoring function compared to other state-of-the-art models.

PEJL: A path-enhanced joint learning approach for knowledge graph completion

<abstract><p>Knowledge graphs (KGs) often suffer from incompleteness. Knowledge graph completion (KGC) is proposed to complete missing components in a KG. Most KGC methods focus on direct relations and fail to leverage rich semantic information in multi-hop paths. In contrast, path-based embedding methods can capture path information and utilize extra semantics to improve KGC. However, most path-based methods cannot take advantage of full multi-hop information and neglect to capture multiple semantic associations between single and multi-hop triples. To bridge the gap, we propose a novel path-enhanced joint learning approach called PEJL for KGC. Rather than learning multi-hop representations, PEJL can recover multi-hop embeddings by encoding full multi-hop components. Meanwhile, PEJL extends the definition of translation energy functions and generates new semantic representations for each multi-hop component, which is rarely considered in path-based methods. Specifically, we first use the path constraint resource allocation (PCRA) algorithm to extract multi-hop triples. Then we use an embedding recovering module consisting of a bidirectional gated recurrent unit (GRU) layer and a fully connected layer to obtain multi-hop embeddings. Next, we employ a KG modeling module to leverage various semantic information and model the whole knowledge graph based on translation methods. Finally, we define a joint learning approach to train our proposed PEJL. We evaluate our model on two KGC datasets: FB15K-237 and NELL-995. Experiments show the effectiveness and superiority of PEJL.</p></abstract>

A lightweight CNN-based knowledge graph embedding model with channel attention for link prediction.

Knowledge graph (KG) embedding is to embed the entities and relations of a KG into a low-dimensional continuous vector space while preserving the intrinsic semantic associations between entities and relations. One of the most important applications of knowledge graph embedding (KGE) is link prediction (LP), which aims to predict the missing fact triples in the KG. A promising approach to improving the performance of KGE for the task of LP is to increase the feature interactions between entities and relations so as to express richer semantics between them. Convolutional neural networks (CNNs) have thus become one of the most popular KGE models due to their strong expression and generalization abilities. To further enhance favorable features from increased feature interactions, we propose a lightweight CNN-based KGE model called IntSE in this paper. Specifically, IntSE not only increases the feature interactions between the components of entity and relationship embeddings with more efficient CNN components but also incorporates the channel attention mechanism that can adaptively recalibrate channel-wise feature responses by modeling the interdependencies between channels to enhance the useful features while suppressing the useless ones for improving its performance for LP. The experimental results on public datasets confirm that IntSE is superior to state-of-the-art CNN-based KGE models for link prediction in KGs.

Metodologia de desenho cultural a partir da perspectiva da filosofia cultural: um caso de ningbo

Abstract: Cultural design integrates cultural content into the design process. It is an important means to realize the innovation of traditional culture in inheritance. Cultural design behavior is subtly influenced by cultural philosophy. Specifically, cultural environment analysis, cultural semantic association and cultural imagery extraction, from the perspective of cultural philosophy, are helpful in realizing the explicitness of designers’ implicit knowledge in the process of encoding and decoding cultural genes. We select Ningbo as a sample to deeply mine the regional cultural genes, explore the generation mode of cultural design, and further propose a framework for building a cultural design knowledge service system. So as to provide methodological guidance for regional cultural design practice to build sustainable cultural design capabilities.

On the manipulation, and meaning(s), of color in food: A historical perspective.

While there has long been public concern over the use of artificial/synthetic food colors, it should be remembered that food and drink products (e.g., red wine) have been purposefully colored for millennia. This narrative historical review highlights a number of reasons that food and drink have been colored, including to capture the shopper's visual attention through to signaling the likely taste/flavor. Over the course of the last century, there has, on occasion, also been interest in the playful, or sometimes even deliberately discombobulating, use of food coloring by modernist chefs and others. The coloring (or absence of color) of food and drink can, though, sometimes also take on more of a symbolic meaning, and, in a few cases, specific food colors may acquire a signature, or branded (i.e., semantic) association. That said, with food color being associated with so many different potential "meanings," it is an open question as to which meaning the consumer will associate with any given instance of color in food, and what role context may play in their decision. Laboratory-based sensory science research may not necessarily successfully capture the full range of meanings that may be associated with food color in the mind of the consumer. Nevertheless, it seems likely that food color will continue to play an important role in dictating consumer behavior in the years to come, even though the visual appearance of food is increasingly being mediated via technological means, including virtual and augmented reality.

From Symptomes of Martirdome to Symptoms of Inclination

The signifier term symptom is strongly associated with the medical register, and its history in English medical writing has been studied quite extensively. This study contributes to our knowledge of the non-medical uses of symptom during the Early Modern period. Drawing on the 1.4-billion-word Early English Books Online corpus, the study examines all extant occurrences of symptom and categorises their usage. The diachronic study shows that non-medical uses of symptom emerged almost immediately after the word came into common use, and that despite its semantic association with medical prognostication and ailments of various kinds, symptom has always been used to some extent as a signifier term referring to positive events and states of being.

The Semantic Association Test (SAT): normative data from healthy Italian participants and a validation study in aphasic patients.

The Semantic Association Test assesses several aspects of Semantic Memory (Categorical, Encyclopedic, Functional, and Visual Encyclopedic associations: CAs, EAs, FAs and VEAs), using a picture-to-picture matching paradigm. Normative data were collected from a group of 329 healthy participants (178 females) with mean 51.1 (range 20-90) years of age and mean 11.89 (range 5-19) years of education. Raw scores of healthy participants, pre-calculated correction factors for age and educational level, and Equivalent Scores are provided. The SAT was validated in a sample of 139 left brain-damaged persons with aphasia (PWA). Both groups (healthy participants and PWA) scored worse in the CA and EA conditions. The performance of the PWA group was overall defective, and global aphasics scored worse than persons with other types of aphasia. However, several PWA did not show impairments in the SAT. Dissociations were also found, with individual PWA showing defective performance confined to a single category. These results present the SAT as a tool that is useful to detect impairments of visual Semantic Memory, providing normative data from healthy participants and a validation study in PWA.