Semantic Space Research Articles

Modeling and Resolving Uncertainty in DIKWP Model

The paper examines the various uncertainties encountered in high-frequency trading (HFT) environments and delves into the multiple challenges faced by HFT firms in navigating the Dodd–Frank Wall Street Reform and Consumer Protection Act (referred to as the “Dodd–Frank Act”), particularly during the initial stages of its enactment. These challenges include the ambiguity surrounding the definition of HFT, the lack of clarity regarding regulatory requirements and boundaries, inconsistencies in enforcement resulting from deviations in understanding the content, and the absence of detailed descriptions of the Act’s provisions. These hurdles significantly impact not only the daily operations of HFT firms but also pose higher demands on their long-term strategic planning and risk management. Drawing upon the Data, Information, Knowledge, Wisdom, and Purpose (DIKWP) model, this study employs an innovative analytical framework. Through the comprehensive application of Cognitive Space, Concept Space, and Semantic Space, it provides a systematic methodology for identifying and analyzing the aforementioned issues. This approach not only aids firms in better comprehending and adhering to complex regulatory requirements but also enables them to explore new business opportunities and competitive advantages while ensuring compliance.

USING THE «METAPHORIZATION» TECHNOLOGY IN MEDIA LITERACY TRAINING

The article is devoted to the analysis of interactive and reflective technology and its use in the process of conducting training on media literacy and critical thinking. The main approaches to the definition of the concept of «metaphorization» in the format of training and scientific categories of thinking are considered. Metaphorization in training is the use of metaphors as a powerful learning tool that promotes deeper understanding and assimilation of the material. This article discusses the role of metaphors in the training process, identifies their main functions and mechanisms of influence on participants. The authors emphasize the ability of metaphors to promote creativity, deeper comprehension of the training material, and more effective communication between the trainer and participants. Considerable attention is paid to the analysis of specific examples of metaphors that have been successfully used in trainings, as well as to the methods of creating them and adapting them to different learning objectives and audiences. The influence of cultural factors on the perception of metaphors is also considered, which requires trainers to have a deeper understanding of the cultural context of their participants. The peculiarities of approaches to the definition of the concept of metaphorization in education are analyzed. It is argued that since each person is a carrier of a special semantic space peculiar only to him or her, many elements of which are metaphorical, it is possible to distinguish a set of individual metaphors in relation to the problem or phenomena under study. On this basis, the author's original technology «metaphorization in training» was created, which has been repeatedly used by the author in working with media trainers in the process of conducting media literacy trainings. The article provides examples of creative projects of the training participants and the author's comments on the use of the metaphorization method for various aspects of media literacy. The author's generalized conclusions on each group work give a systematic view of both the process of media literacy development in our country during Ukraine's liberation war against russia and reveal the main opportunities for using this technology in the process of conducting trainings. The conclusions of the article emphasize the importance of integrating metaphors into the structure of training programs as an effective means of improving the quality of training and motivating participants.

Unsupervised Heterogeneous Graph Neural Networks for One-Class Tasks: Exploring Early Fusion Operators

Heterogeneous graphs are an essential structure that models real-world data through different types of nodes and relationships between them, including multimodality, which comprises different types of data such as text, image, and audio. Graph Neural Networks (GNNs) are a prominent graph representation learning method that takes advantage of the graph structure and its attributes that, when applied to the multimodal heterogeneous graph, learn a unique semantic space for the different modalities. Consequently, it allows multimodal fusion through simple operators such as sum, average, or multiplication, generating unified representations considering the supplementary and complementarity relationships between the modalities. In multimodal heterogeneous graphs, the labeling process tends to be even more costly due to the multiple modalities analyzed, in addition to the imbalance of classes inherent to some applications. In order to overcome these problems in applications that comprise a class of interest, One-Class Learning (OCL) is used. Given the lack of studies on multimodal early fusion in heterogeneous graphs for OCL tasks, we proposed a method based on unsupervised GNN for heterogeneous graphs and evaluated different early fusion operators. In this paper, we extend another work by evaluating the behavior of the main GNN convolutions in the method. We highlight that using operators such as average, addition, and subtraction were the best early fusion operators. In addition, GNN layers that do not use an attention mechanism performed better. In this way, we argue for heterogeneous graph neural networks in multimodal using early fusion simple operators instead of well-often-used concatenation and less complex convolutions.

The Meaning of Hope for Polish Male Patients Dying from Cancer Depending on Their Age: An Interdisciplinary Study with the Use of Osgood's Semantic Differential Method.

Background/Objectives: The subject of this article is the reflection on hope-one of the most important predictors and motivators of human actions. Hope is our response to a threat, and it is also the emotion that allows us to overcome hopelessness and to reduce suffering. Hoping is a human capacity with varying cognitive, emotional, and functional dimensions. Psychological, pedagogical (particularly in the framework of special-needs pedagogy and thanatological pedagogy), and theological reflection on hope can be helpful for dying people. The objective of this study was to characterize hope in the semantic space of individuals in the terminal stage of cancer and to verify whether age is a variable that determines this hope. Methods: To complete the study, the Osgood semantic differential method was applied, as modified by Polish psychologist Dr. Boguslaw Block (the DSN-3 test). The research technique consisted of a therapeutic conversation. Results: Research results show that, in general, those in the terminal stage have positive associations with hope. In all three aspects of the used test, namely the cognitive, emotional, and functional aspects, the highest scores assigned to the perception of hope were obtained from men up to 35 years of age. Depending on the ages of patients, one could observe certain semantic shifts, but they did not prove to be statistically significant. Conclusions: Polish males surveyed at the end of life due to cancer generally perceived hope as a supportive force. Therefore, hope can provide emotional support to patients in the terminal stage of cancer and improve their quality of life.

Perceptual model for semantic representation of design futures practice cases: Towards the development of a design futures repository

Various media and forms of cases or works have promoted the development and dissemination of "Design Futures", making empirical research focusing on practical cases not only valuable but also urgently needed. While heuristic case libraries enhance creativity and efficiency in traditional design, a resource library for Design Futures has not been established. To fill this gap, our preliminary work includes clarifying the perception of cases by different practitioners through semantic representation to establish a perceptual model. In this paper, we propose the typology of Design Futures practice cases. Using desktop research, expert selection, and empirical methods, we constructed a semantic perceptual space and further extracted it into four categories. Combining multivariate statistical techniques and related visualization methods, we examined the distinctions and relationships between semantic words, dimensions, cases, and their types. We have finally established the perceptual model for semantic representation of design futures practice cases, with 4 main perception dimensions (critical, wellbeing, conceptual, and technological) and 13 key semantics, and explored in depth the implications these semantics may contain individually. We further explored the potential of the model in developing a case library. In summary, our research findings provide a framework for representing, retrieving, and evaluating practice cases and support the development of a Design Futures Repository.

Application and research of English composition tangent model based on unsupervised semantic space

Abstract Nowadays, major enterprises and schools vigorously promote the combination of information technology and subject teaching, among which automatic grading technology is more widely used. In order to improve the efficiency of English composition correction, the study proposes an unsupervised semantic space model for English composition tangent, using a Hierarchical Topic Tree Hybrid Semantic Space to achieve topic representation and clustering in English composition; adopts a feature dimensionality reduction method to select a set of semantic features to complete the optimization of the feature semantic space; and combines the tangent analysis algorithm to achieve intelligent scoring of English composition. The experimental data show that the accuracy and F-value of the English composition tangent analysis method based on the semantic space are significantly improved, and the Pearson correlation coefficient between the unsupervised semantic space English composition tangent model and the teacher’s manual grading is 0.8936. The results show that the unsupervised semantic space English composition tangent model has a higher accuracy rate, is more applicable, and can efficiently complete the English composition grading task: essay review task.

The cognitive roots of multimodal symbolic forms with an analysis of multimodality in movies

Condillac’s (1754) “Traité des sensations” is the philosophical background of modern discussions on the relationship between perception and multimodal communication. The differences between perception and communication and the transitions between them are discussed with a focus on odor and color. It becomes clear that even at this primary level, the complex interactions of different modalities are the precondition for effective and rich communication. The second part discusses Cassirer’s “Philosophy of Symbolic Forms” as a relevant framework for multimodality studies. Basic aspects are first commented on with a focus on music and visual art. The interaction is even more complex and rich in the case of language; the difficulty of large symbolic forms is mainly due to semantic composition and only to a lesser degree to syntactic concatenation. The first must merge/blend different semantic spaces. It must allow for the plurality of levels of integration from the lexical level, the level of phrases and sentences, up to texts and discourse. The third part focuses on multimodality in film. It treats the representation of movement and action in (film) narratives, the visual perception and representation/communication of movement and action, and the integration of music, moving images, and language.

Computational reconstruction of mental representations using human behavior

Revealing how the mind represents information is a longstanding goal of cognitive science. However, there is currently no framework for reconstructing the broad range of mental representations that humans possess. Here, we ask participants to indicate what they perceive in images made of random visual features in a deep neural network. We then infer associations between the semantic features of their responses and the visual features of the images. This allows us to reconstruct the mental representations of multiple visual concepts, both those supplied by participants and other concepts extrapolated from the same semantic space. We validate these reconstructions in separate participants and further generalize our approach to predict behavior for new stimuli and in a new task. Finally, we reconstruct the mental representations of individual observers and of a neural network. This framework enables a large-scale investigation of conceptual representations.

Fine-Grained Cross-Modal Semantic Consistency in Natural Conservation Image Data from a Multi-Task Perspective.

Fine-grained representation is fundamental to species classification based on deep learning, and in this context, cross-modal contrastive learning is an effective method. The diversity of species coupled with the inherent contextual ambiguity of natural language poses a primary challenge in the cross-modal representation alignment of conservation area image data. Integrating cross-modal retrieval tasks with generation tasks contributes to cross-modal representation alignment based on contextual understanding. However, during the contrastive learning process, apart from learning the differences in the data itself, a pair of encoders inevitably learns the differences caused by encoder fluctuations. The latter leads to convergence shortcuts, resulting in poor representation quality and an inaccurate reflection of the similarity relationships between samples in the original dataset within the shared space of features. To achieve fine-grained cross-modal representation alignment, we first propose a residual attention network to enhance consistency during momentum updates in cross-modal encoders. Building upon this, we propose momentum encoding from a multi-task perspective as a bridge for cross-modal information, effectively improving cross-modal mutual information, representation quality, and optimizing the distribution of feature points within the cross-modal shared semantic space. By acquiring momentum encoding queues for cross-modal semantic understanding through multi-tasking, we align ambiguous natural language representations around the invariant image features of factual information, alleviating contextual ambiguity and enhancing model robustness. Experimental validation shows that our proposed multi-task perspective of cross-modal momentum encoders outperforms similar models on standardized image classification tasks and image-text cross-modal retrieval tasks on public datasets by up to 8% on the leaderboard, demonstrating the effectiveness of the proposed method. Qualitative experiments on our self-built conservation area image-text paired dataset show that our proposed method accurately performs cross-modal retrieval and generation tasks among 8142 species, proving its effectiveness on fine-grained cross-modal image-text conservation area image datasets.

Dispelling the Fake: Social Bot Detection Based on Edge Confidence Evaluation.

Social bot detection is essential for maintaining the safety and integrity of online social networks (OSNs). Graph neural networks (GNNs) have emerged as a promising solution. Mainstream GNN-based social bot detection methods learn rich user representations by recursively performing message passing along user-user interaction edges, where users are treated as nodes and their relationships as edges. However, these methods face challenges when detecting advanced bots interacting with genuine accounts. Interaction with real accounts results in the graph structure containing camouflaged and unreliable edges. These unreliable edges interfere with the differentiation between bot and human representations, and the iterative graph encoding process amplifies this unreliability. In this article, we propose a social Bot detection method based on Edge Confidence Evaluation (BECE). Our model incorporates an edge confidence evaluation module that assesses the reliability of the edges and identifies the unreliable edges. Specifically, we design features for edges based on the representation of user nodes and introduce parameterized Gaussian distributions to map the edge embeddings into a latent semantic space. We optimize these embeddings by minimizing Kullback-Leibler (KL) divergence from the standard distribution and evaluate their confidence based on edge representation. Experimental results on three real-world datasets demonstrate that BECE is effective and superior in social bot detection. Additionally, experimental results on six widely used GNN architectures demonstrate that our proposed edge confidence evaluation module can be used as a plug-in to improve detection performance.

Decoupling Anomaly Discrimination and Representation Learning: Self-supervised Learning for Anomaly Detection on Attributed Graph

Anomaly detection on attributed graphs is a crucial topic for practical applications. Existing methods suffer from semantic mixture and imbalance issue because they commonly optimize the model based on the loss function for anomaly discrimination, mainly focusing on anomaly discrimination and ignoring representation learning. Graph Neural networks based techniques usually tend to map adjacent nodes into close semantic space. However, anomalous nodes commonly connect with numerous normal nodes directly, conflicting with the assortativity assumption. Additionally, there are far fewer anomalous nodes than normal nodes, leading to the imbalance problem. To address these challenges, a unique algorithm, decoupled self-supervised learning for anomaly detection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD.

VERBAL REPRESENTATIONS OF WEAPONS: A UNIVERSALIA-ORIENTED ANALYSIS

This paper explores the verbal representations of the WEAPON concept in Old English and Old Icelandic texts, examining how irrational knowledge structures, or "nano-myths," are embedded within the inner form of the concept's names through etymological analysis and interdisciplinary comparisons. These "nano-myths" serve as interpretational and categorizational filters, providing insight into the conceptual underpinnings of these language units. The study emphasizes the role of cognitive models as the basis for these conceptual verbalizations. The analytical approach used in this research is rooted in the theory of myth-oriented semiosis, which forms a key component of the interdisciplinary methodology known as "M-logic." This approach involves reconstructing the cognitive premises underlying these language units and mapping them against a universal model of an open system to identify patterns and variations. The identified models are then compared to ascertain the differences and similarities in conceptual representation between Old English and Old Icelandic. The paper's synthetic interpretations suggest that the set of conceptualized semantic features, organized within the hierarchical plane of the universal model, helps define the allomorphic contours of the respective semantic spaces in the two worldviews. The instrumental component of the isomorphic frame-type structure, which reflects the synergetic dynamics of these semantic spaces, is extended in distinct ways in the Old English and Old Icelandic contexts. This differentiation contributes to the allomorphic structure observed in these worldviews, indicating a unique approach to the concept of weapons in each linguistic tradition.

Word Concreteness and Word Originality

Basque is the oldest known spoken language of Western Europe that is not descended from Indo-European. Despite efforts to stop its use from external influences, the Basque people have shown resiliency throughout their history to keep the language alive. However, as is the case with all other languages, Basque has not been immune to influence from neighboring languages; indeed all Basque speakers are bilingual. The question explored here is whether a word’s concreteness using machine translation from Basque to English and English concreteness scores determines if an original Basque word is spoken today. We find that there is a significant difference of concreteness scores between old and contemporary Basque. We also compared old Basque words with common contemporary Basque words in a semantic vector space and found the old words to cluster more tightly than contemporary words suggesting that words with similar semantic vectors are able to retain usage through time.

Возможные миры художественного текста: когнитивно-семантический аспект репрезентации времени (на материале романа В.В. Орлова «Альтист Данилов»)

This article studies the temporal organization of a literary text from the standpoint of a cognitive semantic approach. Literary time is considered in close connection with the meanings that form the semantic space of a text. The correlation of events within which literary time is manifested shows the direction of literary time, which, in its turn, participates in the formation of thinkable worlds. The study aimed to determine and describe the features of the construction of thinkable worlds within the literary time semantically marked in a literary text. The practical significance of the research lies in identifying and describing the principles of structuring possible worlds by means of their temporal coordinates, representing a synthesis of a hero’s physical and psychological time, with the inclusion of markers of historical time in the semantic space of a literary text. The author studied V.V. Orlov’s novel Danilov, the Violist using the inductive-deductive and comparative methods, cognitive and semantic analysis, as well as philological interpretation. A conclusion is drawn that literary time in this novel is of great importance for the organization of thinkable worlds. Its most frequent markers are segodnya (‘today’) and teper’ (‘now’), lexicalizing the cognitive and semantic features of a world which reminds the reader of objective reality, albeit distant in historical time, as well as of a fantasy world, whose properties are unreal. Orlov creates a synthesis of the hero’s physical and psychological time, which can also include historical time (in that case, the reader’s background knowledge is involved, making it possible to correctly decode precedent phenomena). The semantics of literary time in the novel is hierarchical and systemic: textual representatives manifest both universal ideas about time and author’s individual variability in the perception of chronological intervals, which affects the emotional sphere of the reader.

FontCLIP: A Semantic Typography Visual‐Language Model for Multilingual Font Applications

AbstractAcquiring the desired font for various design tasks can be challenging and requires professional typographic knowledge. While previous font retrieval or generation works have alleviated some of these difficulties, they often lack support for multiple languages and semantic attributes beyond the training data domains. To solve this problem, we present FontCLIP – a model that connects the semantic understanding of a large vision‐language model with typographical knowledge. We integrate typography‐specific knowledge into the comprehensive vision‐language knowledge of a pretrained CLIP model through a novel finetuning approach. We propose to use a compound descriptive prompt that encapsulates adaptively sampled attributes from a font attribute dataset focusing on Roman alphabet characters. FontCLIP's semantic typographic latent space demonstrates two unprecedented generalization abilities. First, FontCLIP generalizes to different languages including Chinese, Japanese, and Korean (CJK), capturing the typographical features of fonts across different languages, even though it was only finetuned using fonts of Roman characters. Second, FontCLIP can recognize the semantic attributes that are not presented in the training data. FontCLIP's dual‐modality and generalization abilities enable multilingual and cross‐lingual font retrieval and letter shape optimization, reducing the burden of obtaining desired fonts.

Правовой социальный капитал в современном обществе

The aim of the article is to theoretically substantiate the new scientific concept of “legal social capital” as a leg-islatively formalized semantic legal space based on people’s trust in each other, the system of state power, law enforcement agencies and existing legislation. In order to prevent offenses, the problem of the formation of legal social capital is urgent, which ensures that the rights and interests of all segments of the population are taken into account and contributes to strengthening the country’s sovereignty. Legal social capital is formed on the basis of faith in the fairness of laws, adherence to the rule of law, and respect for legal legislation. The types of legal social capital are: personal, group, organizational, social and international. The main socio-psychological components of legal social capital are: 1) trust in state and law enforcement agencies; 2) asser-tive behavior as the ability and ability to protect one’s rights and interests; 3) high appreciation of the prestige of law enforcement agencies; 4) compliance with legal regulations.

Mapping semantic space: Exploring the higher-order structure of word meaning

Multiple representation theories posit that concepts are represented via a combination of properties derived from sensorimotor, affective, and linguistic experiences. Recently, it has been proposed that information derived from social experience, or socialness, represents another key aspect of conceptual representation. How these various dimensions interact to form a coherent conceptual space has yet to be fully explored. To address this, we capitalized on openly available word property norms for 6339 words and conducted a large-scale investigation into the relationships between 18 dimensions. An exploratory factor analysis reduced the dimensions to six higher-order factors: sub-lexical, distributional, visuotactile, body action, affective and social interaction. All these factors explained unique variance in performance on lexical and semantic tasks, demonstrating that they make important contributions to the representation of word meaning. An important and novel finding was that the socialness dimension clustered with the auditory modality and with mouth and head actions. We suggest this reflects experiential learning from verbal interpersonal interactions. Moreover, formally modelling the network structure of semantic space revealed pairwise partial correlations between most dimensions and highlighted the centrality of the interoception dimension. Altogether, these findings provide new insights into the architecture of conceptual space, including the importance of inner and social experience, and highlight promising avenues for future research.

Chinese-Vietnamese cross-lingual event retrieval method based on knowledge distillation

Cross-lingual event retrieval is an information retrieval task aimed at cross-lingual event retrieval among multiple languages to find text or documents related to a specific event. Specific to Chinese-Vietnamese cross-language event retrieval, it involves using Chinese as a query to retrieve Vietnamese documents related to the query event. The critical issue is how to efficiently align query and document representations with limited resources. Existing cross-language pre-training models are trained on large-scale multilingual corpora, but their training goals do not include explicit language alignment tasks. Due to the uneven distribution of training corpora between different languages, these models have The problem of language bias. Therefore, this linguistic bias is also inherited in cross-lingual retrieval based on these models. To solve this problem, this paper proposes a Chinese-Vietnamese cross-lingual event retrieval method based on knowledge distillation. This approach enables the model to learn good query-document matching features from monolingual retrieval by transferring knowledge from high-resource to low-resource languages. By enhancing the alignment between queries and documents in different languages in a shared semantic space, the method improves the performance of Chinese-Vietnamese cross-lingual event retrieval.

Cross-dataset discriminant subspace learning algorithm for apple leaf diseases identification

Apple has a large planting area and high yield in China, but it is easily affected by diseases. Artificial intelligence technology has achieved good results in apple leaf disease identification. However, the training and testing data in complex environments often come from different collection scenarios. There are significant differences in the training and testing datasets, which leads to a significant decline in the identification performance. To improve the generalization ability of apple leaf disease identification, we develop a cross-dataset discriminant subspace learning (CDDSL) algorithm by utilizing the idea of transfer learning, low-rank sparse representation, and maximum margin neighborhood preserving embedding (NPE) to cross-dataset scenarios. Firstly, based on the transfer learning and low-rank sparse representation, each target sample can be represented by a linear combination of source domain samples. The sparse constraint on the noise matrix weakens the influence of noise in the sample data. Then, CDDSL progressively projects the subspace features into the semantic space and establishes a discriminant classifier. Meanwhile, CDDSL utilizes the maximal margin NPE to improve the intraclass compactness and interclass separability of projection features, which can enhance the image identification performance. The experiments conducted on real-world apple leaf datasets verify the effectiveness of the CDDSL algorithm in cross-dataset scenario.

Personalized Explainable Recommendations for Self-Attention Collaboration

In recommender systems, providing reasonable explanations can enhance users’ comprehension of recommended results. Template-based explainable recommendation heavily relies on pre-defined templates, constraining the expressiveness of generated sentences and resulting in low-quality explanations. Recently, a novel approach was introduced, utilizing embedding representations of items and comments to address the issue of user IDs and item IDs not residing in the same semantic space as words, thus attributing linguistic meaning to IDs. However, these models often fail to fully exploit collaborative information within the data. In personalized recommendation and explanation processes, understanding the user’s emotional feedback and feature preferences is paramount. To address this, we propose a personalized explainable recommendation model based on self-attention collaboration. Initially, the model employs an attention network to amalgamate the user’s historical interaction feature preferences with their user ID information, while simultaneously integrating all feature information of the item with its item ID to enhance semantic ID representation. Subsequently, the model incorporates the user’s comment feature rhetoric and sentiment feedback to generate more personalized recommendation explanations utilizing a self-attention network. Experimental evaluations conducted on two datasets of varying scales demonstrate the superiority of our model over current state-of-the-art approaches, validating its effectiveness.