Semantic Space Research Articles

ChatEV: Predicting electric vehicle charging demand as natural language processing

The increasing popularity of electric vehicles (EVs) in recent times has introduced considerable load conditions for urban power grids and transportation systems, which highlights the importance of accurately predicting charging demand to enhance charging efficiency. However, current forecasting methods still face challenges in effectively aligning diverse data and generating accurate predictions that can be applied to unseen scenarios. To overcome the challenges, this work introduces a novel perspective: employing large language models (LLMs) as EV charging demand predictors. First, we reformulate the prediction task into a text-to-text format, enabling seamless and effective alignment of various features within a unified language semantic space. Subsequently, we fine-tune a LLM using a meta-learning framework to adapt it specifically for EV charging prediction. Through comprehensive evaluations, it has been demonstrated that the proposed model, ChatEV, achieves outstanding performance in EV charging demand forecasting, particularly in scenarios with limited data.

Partial Multi-Label Learning via Exploiting Instance and Label Correlations

The goal of partial multi-label learning is to induce a multi-label classifier from partial multi-label data where each instance is annotated with a number of candidate labels but only a subset of them are valid. Many of the existing studies either fail to fully utilize instance and label correlations to eliminate noisy labels or build an oversimplified multi-label classifier, both of which are unfavorable for the improvement of generalization performance. In this article, we put forward a novel model named Pml-ilc to learn a multi-label classifier from partial multi-label data. Specifically, Pml-ilc first encodes instances and labels into a compact semantic space and takes full advantage of instance and label correlations to eliminate noisy labels. Then, it induces a linear mapping from the feature space to the label space while exploiting label-specific features and instance correlations to facilitate the multi-label classifier learning process. Finally, the above two steps are combined into a joint optimization problem and an efficient alternating optimization procedure is developed to find a satisfactory solution. Extensive experiments show that Pml-ilc achieves superior performance on both real-world and synthetic partial multi-label datasets in terms of different evaluation metrics.

Image evaluation and analysis of fabric with a geometric motif in dress style design

To explore the differences in sensory imagery produced by different geometric patterns and dress silhouettes, this study selected and extracted 4 different types of geometric patterns and 4 typical dress silhouettes as research carriers, determined the research samples through cross-combination, and used 8 pairs of sensory word pairs as research semantic space. Consumer sensory evaluations of the dress samples were collected through a survey questionnaire. The results were analysed using SPSS26.0 software, which showed that three sensory factors affect the appearance of the dress style. According to their main characteristics, they can be named as personality factor, temperament factor, and style factor. In terms of the silhouette of the dress, the neat and regular geometric pattern is most affected by the silhouette of the dress, while the other three types of geometric patterns are relatively weak. In terms of geometric pattern rules, different geometric patterns have different effects on the overall appearance of the dress after being combined with the silhouette of the dress, and some dresses play a certain role in all three factors.

SEMANTIC SPACE OF YOUTH AS A FACTOR IN THE FORMATION OF LIFE COMPETENCE IN THE CONDITIONS OF WAR

The study aims to define the semantic fields of the "life competence" concept and clarify the nature of the relationship between understanding this concept and the setting of life tasks by young people in war. The goal was achieved by solving the following tasks in turn: clarifying the etymology of the "life competence" concept and its content and structural components as semantic fields of understanding this concept in everyday and scientific contexts; studying the semantic space of understanding life competence by young people in war conditions; determining the impact of the peculiarities of understanding the "life competence" concept by young people on their life tasks. The tasks were solved with the help of theoretical (theoretical and methodological analysis, comparison and generalization of results), empirical (semantic differential method, narrative survey method), and mathematical (factor and correlation analyses) methods. The conducted theoretical and empirical research has shown a sufficient cognitive complexity of the "life competence" concept young people's understanding and concepts closely related to it: "life experience", "life task", "difficult life situation", as well as the closeness of semantics to scientific contexts. It has been found that the semantic fields of these concepts are in close direct relationship, which are logically interpreted in the context of everyday thinking and modern psychological science. Defined positive correlations of the criteria for understanding the "life competence" concept by young people with the life tasks that young people set during the war: development, education, family mutual assistance, helping others, solving problems of material support, preserving psychological health, which allowed us to characterize the features of young people semantic space by their life tasks priorities Keywords: life competence, semantic space, difficult life situation, life experience, life task, war, youth

Sentence Embeddings and Semantic Entity Extraction for Identification of Topics of Short Fact-Checked Claims

The objective of this research was to design a method to assign topics to claims debunked by fact-checking agencies. During the fact-checking process, access to more structured knowledge is necessary; therefore, we aim to describe topics with semantic vocabulary. Classification of topics should go beyond simple connotations like instance-class and rather reflect broader phenomena that are recognized by fact checkers. The assignment of semantic entities is also crucial for the automatic verification of facts using the underlying knowledge graphs. Our method is based on sentence embeddings, various clustering methods (HDBSCAN, UMAP, K-means), semantic entity matching, and terms importance assessment based on TF-IDF. We represent our topics in semantic space using Wikidata Q-ids, DBpedia, Wikipedia topics, YAGO, and other relevant ontologies. Such an approach based on semantic entities also supports hierarchical navigation within topics. For evaluation, we compare topic modeling results with claims already tagged by fact checkers. The work presented in this paper is useful for researchers and practitioners interested in semantic topic modeling of fake news narratives.

Three-dimensional Change Detection and Description in Complex Construction Scenarios

Abstract. In large-scale engineering construction scenarios, construction objects and equipment are numerous; their spatial positions and postures change frequently and are complex and varied. Describing the changes between construction entities and the entities themselves in a three-dimensional (3D) geometric space and functional semantic space is challenging. In response to this challenging, we propose a novel workflow to detect and describe the changes in a construction site. First, we add the constraint of object surface continuity to the octree change detection (OCD), exclude the independently changing cells, and improve the change detection robustness. Second, based on the changes in entity elements that occur in the 3D geometric space, we introduce six-type semantics to characterize the changes that occur. Differing from existing change detection semantic description methods that focus on the attribute semantics of changed entity elements, our method focuses on the semantic description of the change process. Finally, for the variations in different semantic types, we propose specific quantization methods that can better quantify the variations in entity elements in 3D geometric space. For the proposed solution, we tested it using two sets of multi-period time-series point cloud data, which can accurately identify the changing construction entities in space and complete the calculation of bridge construction progress, including the building demolition and construction, and the change in the construction apparatus position.

СЕМАНТИЧЕСКАЯ БЛИЗОСТЬ АСТРОНОМИЧЕСКИХ ПОНЯТИЙ, ОБОЗНАЧАЮЩИХ НЕБЕСНЫЕ ТЕЛА

The problem of determining the semantic similarity of astronomical terms denoting celestial objects in a school astronomy course is considered. A distributive method is used, which consists in comparing the distributions of concepts in the astronomy textbook. With the help of special computer programs, punctuation marks and stop words are removed from the text, the number of mentions of various terms is deter-mined, the cosine measure of proximity and the semantic distance between concepts are calculated. This allows: 1) to reveal frequently used astronomical concepts denoting celestial bodies; 2) to obtain matrices of proximity and semantic distances between the concepts of "galaxy", "star", "Sun", "planet", "black hole", "white dwarf", etc.; 3) to create a mental map of the celestial bodies that make up the Solar system, taking into account the distances between the terms designating them 4) to build clouds of concepts "types of stars", "Earth – star – Universe". To model the semantic space of the textbook, the Graf.pas computer program is used, which randomly moves vertices in 2D or 3D space, each time calculating the potential energy W of the elastic rods connecting them and choosing such an arrangement of vertices that W is minimal. It is believed that the closely located vertices are connected by rigid rods, and the far removed ones are connected by elastic rubber threads.

Diffusion‐based Human Motion Style Transfer with Semantic Guidance

Abstract3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN‐based methods necessitate datasets with balanced style distribution and content/style labels to train the clustered latent space. However, we may encounter a single unseen style example in practical scenarios, but not in sufficient quantity to constitute a style cluster for AdaIN‐based methods. Therefore, in this paper, we propose a novel two‐stage framework for few‐shot style transfer learning based on the diffusion model. Specifically, in the first stage, we pre‐train a diffusion‐based text‐to‐motion model as a generative prior so that it can cope with various content motion inputs. In the second stage, based on the single style example, we fine‐tune the pre‐trained diffusion model in a few‐shot manner to make it capable of style transfer. The key idea is regarding the reverse process of diffusion as a motion‐style translation process since the motion styles can be viewed as special motion variations. During the fine‐tuning for style transfer, a simple yet effective semantic‐guided style transfer loss coordinated with style example reconstruction loss is introduced to supervise the style transfer in CLIP semantic space. The qualitative and quantitative evaluations demonstrate that our method can achieve state‐of‐the‐art performance and has practical applications. The source code is available at https://github.com/hlcdyy/diffusion-based-motion-style-transfer.

Correction to: Measuring the semantic headedness of English blends with token-based semantic vector space modeling: a corpus-based study

Correction to: Measuring the semantic headedness of English blends with token-based semantic vector space modeling: a corpus-based study

Mapping and modeling the semantic space of math concepts

Mathematics is an underexplored domain of human cognition. While many studies have focused on subsets of math concepts such as numbers, fractions, or geometric shapes, few have ventured beyond these elementary domains. Here, we attempted to map out the full space of math concepts and to answer two specific questions: can distributed semantic models, such a GloVe, provide a satisfactory fit to human semantic judgements in mathematics? And how does this fit vary with education? We first analyzed all of the French and English Wikipedia pages with math contents, and used a semi-automatic procedure to extract the 1000 most frequent math terms in both languages. In a second step, we collected extensive behavioral judgements of familiarity and semantic similarity between them. About half of the variance in human similarity judgements was explained by vector embeddings that attempt to capture latent semantic structures based on cooccurence statistics. Participants' self-reported level of education modulated familiarity and similarity, allowing us to create a partial hierarchy among high-level math concepts. Our results converge onto the proposal of a map of math space, organized as a database of math terms with information about their frequency, familiarity, grade of acquisition, and entanglement with other concepts.

QSIM: A Quantum-inspired hierarchical semantic interaction model for text classification

Semantic interaction modeling is a fundamental technology in natural language understanding that guides models to extract deep semantic information from text. Currently, the attention mechanism is one of the most effective techniques in semantic interaction modeling, which learns word-level attention representation by measuring the relevance between different words. However, the attention mechanism is limited to word-level semantic interaction, it cannot meet the needs of fine-grained interactive information for some text classification tasks. In recent years, quantum-inspired language modeling methods have successfully constructed quantized representations of language systems in Hilbert spaces, which use density matrices to achieve fine-grained semantic interaction modeling.This paper presents a Quantum-inspired hierarchical Semantic Interaction Model (QSIM), which follows the sememe-word-sentence language construction principle and utilizes quantum entanglement theory to capture hierarchical semantic interaction information in Hilbert space. Our work builds on the idea of the attention mechanism and extends it. Specifically, we explore the original semantic space from a quantum theory perspective and derive the core semantic space using the Schmidt decomposition technique, where: (1) Sememe is represented as the unit vector in the two-dimensional minimum semantic space; (2) Word is represented as reduced density matrices in the core semantic space, where Schmidt coefficients quantify sememe-level semantic interaction. Compared to density matrices, reduced density matrices capture fine-grained semantic interaction information with lower computational cost; (3) Sentence is represented as quantum superposition states of words, and the degree of word-level semantic interaction is measured using entanglement entropy.To evaluate the model’s performance, we conducted experiments on 15 text classification datasets. The experimental results demonstrate that our model is superior to classical neural network models and traditional quantum-inspired language models. Furthermore, the experiment also confirms two distinct advantages of QISM: (1) flexibility, as it can be integrated into various mainstream neural network text classification architectures; and (2) practicability, as it alleviates the problem of parameter growth inherent in density matrix calculation in quantum language model.

Generalized zero-sample industrial fault diagnosis with domain bias

Generalized zero-sample fault diagnosis (GZSFD) is a challenging task involving the diagnosis of all samples from both previously seen and unseen faults. However, the scarcity of unseen samples for training causes that existing methods are hindered by domain bias, where unseen faults are more likely to be misclassified as seen faults. In this article, an efficacious solution is proposed by constructing an unseen fault detector for test samples in GZSFD with domain bias, which utilizes the detected unseen-sample knowledge to enhance the diagnosis performance. Specifically, a ResNet-based one-dimensional convolutional neural network is designed for high-quality feature extraction. Also, a Kullback–Leibler divergence-based distribution threshold detector is constructed for the identification of test samples. Afterwards, test samples are detected and distinguished into seen or unseen classes. In detected unseen classes, a zero-sample fault diagnosis (ZSFD) problem is undertaken, while in detected seen classes, a sub-GZSFD problem is addressed. For ZSFD tasks, to leverage the unseen samples in the test set, a clustering-based scheme without a predefined cluster number is used for the detected unseen fault. For sub-GZSFD tasks, combined with classification results in the ZSFD task, two embedding strategies are proposed to further mitigate the domain bias. They learn a shared weight and the optimal weights of semantic attributes from the feature space to the semantic embedding space, respectively. Using the shared fine-grained semantic attribute descriptions as auxiliary information, the final fault category can be determined. Experimental results showcase that the proposed strategies effectively alleviate the domain bias in GZSFD tasks.

Word vector embedding and self-supplementing network for Generalized Few-shot Semantic Segmentation

Under the condition of sufficient base class samples and a few novel class samples, Generalized Few-shot Semantic Segmentation (GFSS) classifies each pixel in the query image as base class, novel class, or background. A standard GFSS approach involves two training stages: base class learning and novel class updating. However, inter-class interference and information loss which contribute to the poor performance of GFSS, have not been synthetical considered. To address the problem, we propose an Embedded-Self-Supplementing Network (ESSNet), i.e., semantic word embedding and query set self-supplementing information to enhance segmentation accuracy. Specifically, the semantic word embedding module employs distance information between word vectors to assist the model in learning the distance between class prototypes. In order to transform the semantic word vector prototypes from the semantic space to the visual embedding space, we designed a triplet loss function to supervise the word vector embedding module, where the word vector prototype serves as an anchor and positive-negative samples are collected among the general features of the support image. To compensate for the information loss caused by using prototypes to represent classes, we propose a self-supplementing module to mine the information contained in the query image. Specifically, this module first makes a preliminary prediction on the query image, then selects high-confidence area to form pseudo labels, and finally uses pseudo labels to extract query prototypes to supplement the missing information. Extensive experiments on PASCAL-5i and COCO-20i show that ESSNet has superior performance and outperforms state-of-the-art methods in all settings.

Neural representations of concreteness and concrete concepts are specific to the individual.

Different people listening to the same story may converge upon a largely shared interpretation while still developing idiosyncratic experiences atop that shared foundation. What linguistic properties support this individualized experience of natural language? Here, we investigate how the "concrete-abstract" axis - i.e., the extent to which a word is grounded in sensory experience - relates to within- and across-subject variability in the neural representations of language. Leveraging a dataset of human participants of both sexes who each listened to four auditory stories while undergoing functional MRI, we demonstrate that neural representations of "concreteness" are both reliable across stories and relatively unique to individuals, while neural representations of "abstractness" are variable both within individuals and across the population. Using natural language processing tools, we show that concrete words exhibit similar neural representations despite spanning larger distances within a high-dimensional semantic space, which potentially reflects an underlying representational signature of sensory experience - namely, imageability - shared by concrete words but absent from abstract words. Our findings situate the concrete-abstract axis as a core dimension that supports both shared and individualized representations of natural language.Significance Statement The meaning of spoken language is often ambiguous. As a result, people may form different interpretations despite being presented with the same information. What properties of language does the brain leverage to form this diverse, individual experience? Analyses of functional MRI data demonstrated that "concreteness", the extent to which language is related to sensory experience, evoked reliable neural patterns that were unique to individual subjects and allowed us to identify individuals solely based on their neural data. Application of machine learning methods showed that sets of concrete concepts, but not abstract concepts, show stable neural patterns, potentially due to a sensory signature: imageability. Overall, this study characterizes concreteness as a central property supporting the individualized experience of real-world language.

Communication in the Mirror of Social Semiotics

Introduction. The subject of this article is communicative resources, which are selected by partners from a huge variety of linguistic means, functional styles, rhetorical techniques, and subject activities, and through which a common semantic space between individuals is generated.Methodology and sources. As a methodological platform we propose the principles of praxis-oriented social semiotics. Being one of the relatively late trends of semiotic research, social semiotics focuses attention not so much on signs or sign systems as on social signifying practices as regular, repetitive, recognisable types of actions: the actions of communication participants are endowed with the properties of sign systems through which relations between individuals are discovered, made visible and meaningful. The mechanisms of meaning production, from the point of view of the participants of the event, are analysed using the concept of ‘discursive practices’, understood as speech actions in order to solve a variety of practical interpersonal tasks.Results and discussion. As an individual learns a variety of interpersonal discursive practices, different relational systems become available to him/her. Specific discursive practices allow individuals to present different versions of their self, justify their actions, maintain dominance and/or subordination relations, thus demonstrating mastery of the communicative situation. Following the principles of praxis-oriented social semiotics, it can be argued that interpersonal relationships involve what can be called a discourse of trust, personal involvement in relationships, intimacy/closeness.Conclusion. The described symbolic regulators allow not only to semiotically comprehend the social positions of interacting parties, but also to offer self-control procedures and an arsenal of communicative actions to the participants of interpersonal communication as means of behaviour management in situations of interpersonal communication.

Decoupled semantic graph neural network for knowledge graph embedding

Knowledge graph embedding (KGE) learns an embedding space for a more accurate representation of entities and relations. Although the KGE model has proliferated, it often fails to fully capture the rich semantics in knowledge graphs. Some studies attempt to apply decoupling methods to decompose node representations, yet they neglect the semantic noise generated during the decoupled process. To address these issues, we introduce the decoupled semantic graph network for KGE (named DSGNet), which employs a novel approach that combines semantic decoupling with structural awareness. DSGNet begins by projecting the knowledge graph into distinct semantic spaces, ensuring minimal correlation between them to achieve effective semantic decoupling. To mitigate semantic noise, a top-k sampling technique is applied to the decoupled graphs. DSGNet then aggregates these different semantic graphs using a relation-aware aggregation module, followed by a multi-layer aggregation process for enhanced node representation. The extensive experiments demonstrate that DSGNet performs competitively on two popular datasets. We make our code publicly available at https://github.com/HubuKG/DSGNet.

Center-enhanced video captioning model with multimodal semantic alignment

Video captioning aims at automatically generating descriptive sentences based on the given video, establishing an association between the visual contents and textual languages, has attracted great attention and plays a significant role in many practical applications. Previous researches focus more on the aspect of caption generation, ignoring the alignment of multimodal feature and just simply concatenating them. Besides, video feature extraction is usually done in an off-line manner, which leads to the fact that the extracted feature may not adapted to the subsequent caption generation task. To improve the applicability of extracted features for downstream caption generation and to address the issue of multimodal semantic alignment fusion, we propose an end-to-end center-enhanced video captioning model with multimodal semantic alignment, which integrates feature extraction and caption generation task into a unified framework. In order to enhance the completeness of semantic features, we design a center enhancement strategy where the visual–textual deep joint semantic feature can be captured via incremental clustering, then the cluster centers can serve as the guidance for better caption generation. Moreover, we propose to promote the visual–textual multimodal alignment fusion by learning the visual and textual representation in a shared latent semantic space, so as to alleviate the multimodal misalignment problem. Experimental results on two popular datasets MSVD and MSR-VTT demonstrate that the proposed model could outperform the state-of-the-art methods, obtaining higher-quality caption results.

Measuring the semantic headedness of English blends with token-based semantic vector space modeling: a corpus-based study

Abstract This article analyzes the semantic headedness of English blends with distributional semantics methods. The semantic head of a blend is the source word that transfers its semantic information to the blend as a whole. For example, a sitcom is a kind of comedy. But is FedEx a kind of express, and is wi-fi a kind of fidelity? We use corpus data and token-based semantic vector space modeling in order to address these questions. Specifically, we investigate whether Plag’s ternary division of endocentric, exocentric, and coordinative compounds based on semantic headedness can also be applied to English blends, and whether the general tendency of semantic right-headedness can be observed for all three subtypes. We analyze a dataset of fifty-five blends and their respective source words, using data from the Corpus of Contemporary American English and the English Web Corpus 2021. We measure the degree of semantic similarity between each blend and its two source words. The results show that for most endocentric blends, the hypothesis of semantic right-headedness holds true. At the same time, exocentric blends and coordinative blends are shown to behave differently. We conclude that Plag’s classification offers a useful point of departure for the semantic analysis of blends and that distributional semantics methods can provide new insights into their semantic behavior.

STRUCTURAL AND SEMANTIC ORIGINALITY OF THE SEMANTIC FIELD ‟POWER” IN VLADIMIR MAKSIMOV’S NOVEL ‟TO LOOK INTO THE ABYSS”

The article characterises the semantic field ‟Power” in the novel by the famous Russian prose writer of the 2nd half of the 20th century, Vladimir Maksimov (1930–1995). The purpose of the study is a comprehensive analysis of the structural and semantic features of the field, determination of the originality of the textual functioning of its core components, which are the semantic dominants of the work, actively involved in the organisation of the narrative, in the artistic depiction of historical events and the creation of images of literary characters. The theoretical concepts of the semantic field and semantic space of the text, which unites its conceptual, denotative and emotive meanings, are defined. Linguistic modelling of the field structure is based on the principles of discourse analysis of the text and is determined by the specific linguistic personality of the writer, genre-stylistic and plot-compositional features of the work. Characteristic of component composition of the field, its core, centre and periphery, microfields is given. Semantic connections and intersections of field components are determined with contextual synonymy and antonymy revealed. The core of the field includes the key lexemes “power”, “strength”, “leader”, “will”. The semantic field unites five microfields: the central part of the field structure includes the microfields ‟White-Guard Power of Alexander Kolchak” and ‟Soviet Power of Vladimir Lenin”; the peripheral zone includes the microfields ‟Power of Social Elements”, ‟Military Force of Foreign Intervention” and ‟Power of Selfless and unselfish Love”. The semantic dominants of the text, being the key components of the field, contribute to the dynamics of the narrative, create an artistic chronotope, reflect the author’s position, and convey the bright features of the writer’s linguistic personality.

CFNet: Automatic multi-modal brain tumor segmentation through hierarchical coarse-to-fine fusion and feature communication

Automatic segmentation of brain tumors employing images from multi-modalities is important for preoperative diagnosis and prognostic assessment. The rich complementary information contained within multi-modal images allows for improved brain tumor segmentation performance when models are trained on multi-modal data. However, accurate segmentation of small lesion regions from medical images remains challenging, due to the irregular shapes and low boundary contrast of brain gliomas. To address these challenges, we propose a coarse-to-fine feature fusion network (CFNet) that effectively incorporates multi-modal image features through modal interaction, semantic perception, and feature fusion. Specifically, the modality cross-attention fusion module is proposed introducing complementary features and mapping them into a unified semantic space to learn complementary representations between modalities. Furthermore, the multi-scale context perception module enables the model to focus on multi-scale lesion fine-grained information while capturing deep semantics. Moreover, the further fusion of fine-grained features with coarse-grained features enhances edge features and the complementary of features. We evaluate the proposed CFNet on two public brain tumor segmentation datasets BraTS2019 and BraTS2020. Experimental results show that the proposed framework outperforms state-of-the-art methods in Dice score, HD95, Sensitivity, demonstrating the effectiveness of CFNet on brain tumor segmentation. Code will be available at https://github.com/YaruC/CFNet.