Semantic Hierarchy Research Articles

The Significance of Semantic Hierarchy and Canonicity in Sentence Comprehension: A Study of Persian-speaking Patients With Alzheimer

Introduction: A lot of research in diverse languages has tried to scrutinize the impact of canonicity upon the performance of patients with Alzheimer's disease. Regarding the gap in the Persian setting, this study tried to delve into the nature of this deficit in patients with Alzheimer. Materials and Methods: This is a case series study, and our subjects included 2 Persian- speaking monolingual patients with Alzheimer and 5 healthy elderly individuals matched with each other according to parameters like educational degree, vernacular tongue, and homeland. The categories to be tested included subject agentive, subject experiencer, object experiencer, and object cleft constructions. Results: The results of the sentence completion task demonstrated that problems would emerge when patients with Alzheimer try to comprehend the syntactic structures belonged to 2, 3, and 4 categories. Conclusion: Our findings would demonstrate that patients with Alzheimer have many challenges when trying to map syntactic representation onto semantic realization. This type of deficit escalates when patients attempt to assign thematic roles to psychological predicates. As for the clinical implication of the research, it was recommended that the type of structures utilized by neuropsychiatrists for the communicative purpose be chosen from utterances that are in line with the mapping strategy.

Financial Early Warning System Model Combining Hybrid Semantic Hierarchy with Group Method of Data Handling Neural Network for Detection of Banks’ Risks

Banks, financial, and credit institutions encountering the weakening financial system and increased risk factors cause high inflation and great losses for an economy. Detecting financial risks in advance could help financial institutions avoid losses, and the financial system could be eventually affected less. Early warning systems for banks could be helpful to identify financial risks and take measures to deal with hazardous situations. Various approaches have already been put forward. However, inaccuracy issues in risk detection are one of the main issues. Combining semantic hierarchy with the GMDH neural network to predict financial risks is proposed. A semantic hierarchy approach based on converting risk-related values and picking influential variables could be practical in risk detection. Besides, the GMDH algorithm utilizing neural networks based on available data has the capability of predicting possible risks that could occur in the future. The outcomes of the proposed method when compared to non-data mining methods suggest that it improves accuracy by almost 20%.

Semantic scope restrictions in complex verb constructions in Dutch

AbstractThis article addresses the question of how and why verbs combine in complex verb constructions in Dutch. We discuss introspective data reported in reference grammars and add evidence from corpus data to uncover the systematic ways in which Dutch verbs combine. Our analysis shows that verbs expressing meanings such as tense, aspect, modality and evidentiality are organized in a semantic scope hierarchy; that is, some verb meanings systematically have scope over others but not the other way round. We argue that this scope hierarchy reflects hierarchies of functional categories, elaborated in both functional and generative frameworks.

Hierarchical classification of data with long-tailed distributions via global and local granulation

Automated learning from datasets with a long-tailed distribution has gradually become a research hotspot due to the increasing complexity of large-scale real-world datasets. Existing solutions to long-tailed data classification usually involve re-balancing strategies for global optimization, which can achieve satisfactory results. However, re-balancing strategies tend to alter the original data. In this paper, we propose a knowledge granulation method based on global and local granulation to assist the hierarchical classification of long-tailed data without altering the original data. Firstly, a global classifier is constructed based on the WordNet knowledge organization’s hierarchical structure, which is used to granulate the global data from coarse to fine. Secondly, a local hierarchical classifier adapted to tail data is constructed for tail classes that contain few samples. The hierarchical structure of this local classifier is obtained by granulating the data via spectral clustering rather than by using the semantic hierarchy of classes. Finally, the global classifier is used to preliminarily classify samples, then uncertain samples are further classified by the tail local classifier. Experimental results show that the proposed method outperforms several state-of-the-art models designed for the hierarchical classification of long-tailed data.

Memory decay distinguishes subtypes of gist

Memories are thought to become more gist-like over time. Multiple related memories might form generalized memory representations, losing specific details but enhancing or retaining gist. The time course within which gist memory emerges, however, is the subject of less consensus. To address this question, we focused our design on four kinds of gist: inferential gist (relations extracted across non-contiguous events), statistical learning (regularities extracted from a series), summary gist (a theme abstracted from a temporally contiguous series of items), and category gist (characterization of a stimulus at a higher level in the semantic hierarchy). Seventy participants completed memory encoding tasks addressing these types of gist and corresponding retrieval tasks the same evening, the morning after, and one week later, as well as an MRI at a later time point. We found little evidence that gist slowly emerges over time or that gist traces are more resistant to forgetting than detail traces. Instead, we found that initial gist memory shortly after encoding was either retained over time or decayed. Inferential gist and statistical learning were retained over a week, whereas memory for category and summary gist decayed. We discuss several interpretations for differences between these two subtypes of gist. Individual differences in REM or slow-wave sleep and hippocampal volumes did not predict changes in memory for these four kinds of gist in a healthy young adult population.

Multiclass semantic segmentation for digitisation of movable heritage using deep learning techniques

<p class="VARAbstract">Digitisation processes of movable heritage are becoming increasingly popular to document the artworks stored in our museums. A growing number of strategies for the three-dimensional (3D) acquisition and modelling of these invaluable assets have been developed in the last few years. Their objective is to efficiently respond to this documentation need and contribute to deepening the knowledge of the masterpieces investigated constantly by researchers operating in many fieldworks. Nowadays, one of the most effective solutions is represented by the development of image-based techniques, usually connected to a Structure-from-Motion (SfM) photogrammetric approach. However, while images acquisition is relatively rapid, the processes connected to data processing are very time-consuming and require the operator’s substantial manual involvement. Developing deep learning-based strategies can be an effective solution to enhance the automatism level. In this research, which has been carried out in the framework of the digitisation of a wooden maquettes collection stored in the ‘Museo Egizio di Torino’, using a photogrammetric approach, an automatic masking strategy using deep learning techniques is proposed, to increase the level of automatism and therefore, optimise the photogrammetric pipeline. Starting from a manually annotated dataset, a neural network was trained to automatically perform a semantic classification to isolate the maquettes from the background. The proposed methodology allowed the researchers to obtain automatically segmented masks with a high degree of accuracy. The workflow is described (as regards acquisition strategies, dataset processing, and neural network training). In addition, the accuracy of the results is evaluated and discussed. Finally, the researchers proposed the possibility of performing a multiclass segmentation on the digital images to recognise different object categories in the images, as well as to define a semantic hierarchy to perform automatic classification of different elements in the acquired images.</p><p><strong>Highlights:</strong></p><ul><li><p>In the framework of movable heritage digitisation processes, many procedures are very time-consuming, and they still require the operator’s substantial manual involvement.</p></li><li><p>This research proposes using deep learning techniques to enhance the automatism level in the generation of exclusion masks, improving the optimisation of the photogrammetric procedures.</p></li><li><p>Following this strategy, the possibility of performing a multiclass semantic segmentation (on the 2D images and, consequently, on the 3D point cloud) is also discussed, considering the accuracy of the obtainable results.</p></li></ul>

Peculiarities of actualization of sociological, cultural and episodic memory components in the works of the Great Patriotic War

The article studies a complex contaminated process of actualization of semantic components, which explicate various spheres of intentional objectification of general content in the texts of the precedent world “The Great Patriotic War”. The focuses, first of all, on the axiological basis for integrating the components of comparing personal understanding of the precedent phenomenon and its perception in culture. The dominants of psychic and socially oriented elements of the value space acquire their verbalization in the intimization sphere on the basis of texts of special cultural significance. They are analyzed on the basis of the hermeneutic method, which allows revealing the greatest number of facets of both the basic, nuclear area of verbalization, and to delimit the etymological, passive elements of the semantic hierarchy. In addition, in the process of analyzing the core and periphery, the most effective ways of verbalization and intimization of individual overtones of cultural concepts are determined. Within the framework of identifying the mechanisms of reflexive understanding of the phenomena of “feat”, “suffering”, “anger”, the initial contaminated space of modification of nuclear, etymological, historical and personal peripheral components in their inextricable interaction and mutual influence is recreated. The essence of the dismembered diegetic narration as a key technique for guiding the recipient into the process of derivation of the general content of the work with the formation of a common space of perception and understanding is revealed. The key principles of the reader’s presentation and awareness of the “intimacy” of the narrative with mutual reflexive assessment of the event by the reader and the reader’s hypothetical attitude by the author of the work are described. On the basis of the author’s intentional and unconscious reader’s social reflection in the process of actualizing the components of sociocultural memory within the framework of the precedent world of the Great Patriotic War, a complex conceptual-valency space with a multilevel structure is formed in the linguocultural consciousness of the Russian-speaking community, including the components of the author’s episodic memory.

Hierarchical-aware relation rotational knowledge graph embedding for link prediction

Knowledge graph embedding, as the upstream task of link prediction which aims to predict new links between entities under the premise of known relations, its reliability greatly affects the performance of link prediction. However, previous distance-based models focus on modeling complicated relation patterns while ignoring the semantic hierarchy of knowledge graph, from TransE to RotatE. In this setting, all entities are regarded as the same type, and the fact that different entities belong to different levels is neglected. Therefore, we propose the general form of RotatE, the hierarchical-aware relation rotational knowledge graph embedding (HA-RotatE), to model the hierarchical-aware knowledge graph. HA-RotatE represents entities and relations as complex vectors and uses different moduli of entity embeddings to indicate the different hierarchical levels they belong to. The transformation of modulus and rotation from head entity to tail entity depends on different relations. Some relations are used to link entities of the same level, and others are used to link entities of different levels. We adopt the shared modulus transformation parameter method for avoiding overfitting. As the general form of RotatE, HA-RotatE also has the ability to model and infer various relation modes, i.e., symmetry/antisymmetric, inversion and composition. On benchmark datasets WN18RR and FB15k-237, the experiments on link prediction tasks show that: (1) HA-RotatE can effectively model the semantic hierarchy of the knowledge graph; (2) Compared with competitive benchmarks, our model substantially outperforms them in most metrics.

GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild.

We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon the backbone of WordNet structure [1] and it populates the majority of over 560 classes of moving objects and 87 motion patterns, magnitudes wider than the most recent similar-scale counterparts [19], [20], [23], [26]. By releasing the large high-diversity database, we aim to provide a unified training and evaluation platform for the development of class-agnostic, generic purposed short-term trackers. The features of GOT-10k and the contributions of this article are summarized in the following. (1) GOT-10k offers over 10,000 video segments with more than 1.5 million manually labeled bounding boxes, enabling unified training and stable evaluation of deep trackers. (2) GOT-10k is by far the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population, which ensures a comprehensive and relatively unbiased coverage of diverse moving objects. (3) For the first time, GOT-10k introduces the one-shot protocol for tracker evaluation, where the training and test classes are zero-overlapped. The protocol avoids biased evaluation results towards familiar objects and it promotes generalization in tracker development. (4) GOT-10k offers additional labels such as motion classes and object visible ratios, facilitating the development of motion-aware and occlusion-aware trackers. (5) We conduct extensive tracking experiments with 39 typical tracking algorithms and their variants on GOT-10k and analyze their results in this paper. (6) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard. The annotations of GOT-10k's test data are kept private to avoid tuning parameters on it.

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis

Despite the great success of Generative Adversarial Networks (GANs) in synthesizing images, there lacks enough understanding of how photo-realistic images are generated from the layer-wise stochastic latent codes introduced in recent GANs. In this work, we show that highly-structured semantic hierarchy emerges in the deep generative representations from the state-of-the-art GANs like StyleGAN and BigGAN, trained for scene synthesis. By probing the per-layer representation with a broad set of semantics at different abstraction levels, we manage to quantify the causality between the layer-wise activations and the semantics occurring in the output image. Such a quantification identifies the human-understandable variation factors that can be further used to steer the generation process, such as changing the lighting condition and varying the viewpoint of the scene. Extensive qualitative and quantitative results suggest that the generative representations learned by the GANs with layer-wise latent codes are specialized to synthesize various concepts in a hierarchical manner: the early layers tend to determine the spatial layout, the middle layers control the categorical objects, and the later layers render the scene attributes as well as the color scheme. Identifying such a set of steerable variation factors facilitates high-fidelity scene editing based on well-learned GAN models without any retraining (code and demo video are available at https://genforce.github.io/higan ).

Learning Gaussian Hierarchy Embedding for Relation Prediction in Knowledge Graph

Knowledge graph embedding methods, which transform high-dimensional and complex graph contents into low-dimensional vectors (or matrices, tensors) representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as vectors in a low-dimensional embedding space, ignoring the semantic hierarchy and the uncertainty present in the real-world graphs. To address this challenge, in this paper, we propose GHAKE, Gaussian Hierarchy Knowledge Graph Embedding, a novel graph embedding method that preserves both semantic hierarchy and node uncertain effectively and efficiently in an end-to-end manner. GHAKE effectively models uncertainty through Gaussian embeddings, and models semantic hierarchy via mapping entities into the polar coordinate system. In our comprehensive experiments, we evaluate GHAKE on real-world graphs, and the results demonstrate that can effectively model the semantic hierarchies and the uncertain of entities in knowledge graphs, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.

A comprehensive cognitive-perceptual model of analysis for contextually determined components of a conceptualized term

The authors analyze major features of complex multidisciplinary analysis models of the recipient’s perceptual capacity related to desobjectifying contextually determined transdisciplinary borrowing of newly emerging components within a semantic hierarchy. Critical analysis and comparison are applied to some alternative approaches in linguistic studies of transdisciplinary terminologization. There is a role revealed, which belongs to the cognitive-perceptual aspect in the respective knowledge field. The comprehensive phenomenon of component transgression within the meaning hierarchy is viewed from different angles: metaphoric and metonymic explication, and from the stance of conceptual integration of mental spaces and grammatical constructions of implicit meaning generation. The semantic foundations of the frame & semantic model of the borrowing theory serve a prototype of a comprehensive analytical model relevant not only in Linguistics, yet in other humanities (Literature, Psychology, Sociology). The comprehensive method of bottom-up analysis in studying explication of contextually determined overtones (forced reinterpretation of terms and terminoids) implies desobjectification of the semantic hierarchy at several levels. The analysis suggests that standard linguistic mechanisms can be employed through deautomation in the said cognitive modeling function. Reactivating a prototypical mental image within a new reflexive space is viewed as the most effective way of explicating the respective components.

О ЧЕМ МЕЧТАЮТ РОССИЯНЕ? ФУНКЦИОНИРОВАНИЕ ЛЕКСЕМ «МЕЧТАТЬ», «МЕЧТА», «МЕЧТАНИЕ» В СОВРЕМЕННОМ МЕДИАТЕКСТЕ(НА МАТЕРИАЛЕ ПУБЛИКАЦИЙ ИНФОРМАЦИОННОГО ПОРТАЛА «ЛЕНТА.РУ»)

The article analyzes the syntagmatic connections of the words “to dream”, “dream”, “dreaming” based on the materials of the news portal “Lenta. ru”. The phrases found in the corpus of texts under consideration (which comprised more than three author’s sheets) with those words represent the semantic core of the concept “dream” and the corresponding fragment of the journalistic picture of the world – to the extent that this fragment was presented in the publications of 2019–2021 of the media selected for research. The journalistic picture of the world is understood by the author of the article as a kind of functional-style picture of the world, i.e. as a communicatively conditioned version of the linguistic picture of the world, which, fixing the specifics in the life of the people, stores information about the world and is “a vivid reflection of the character and worldview of the people” [Bulygina, Shmelev 1997, p. 481]. The journalistic picture of the world created by the mass media influences the conceptual picture of the world of their addressees, including the semantic content and hierarchy of culturally significant concepts. Thus, studying the syntagmatic connections of the words “to dream”, “dream”, “dreaming” in the publications of “Lenta.ru”, we identify modern ideas about the semantic core of the concept “dream”, which are fixed in the journalistic picture of the world of the media under consideration and broadcast to the audience of the publication.

What psych verbs and other verbs disclose about the role of Semantic Prominence and Thematic Hierarchy in affixal selection

This paper analyses the construction of deverbal adjectives in European Portuguese, focusing on the interface between morphology and semantics, specifically on the role of Thematic Hierarchy and Semantic Prominence on affixal selection.Supported by paradigmatic morphology, the paper shows that suffixes that work in macro-paradigms of deverbal adjectives establish a relationship with specific semantic features of the lexical-semantic structure of the base verb in order to construct the derivative. The analysis concludes that suffixes are sensitive to thematic hierarchy, which is based on the semantic prominence of features of the verbs’ theta-roles at work in the paradigm. Data from psych verbs is highly relevant to this finding.The paper is dedicated to Professor Ana Maria Brito, who has always been keenly aware that scientific knowledge is not confined to a specific theory.

User interfaces ontology in the cybernetic model of intelligent systems

A model of an intelligent system is proposed for implementing the control and professional use of a knowledge collections related to subject area of software interfaces with external users. The basis of formalization is an abstract model of an intelligent system. It is based on coordinated and balanced invariants of the knowledge representation formalism model. Invariants set includes classes of morphisms for abstract knowledge processing modelling with morphisms' domains, invariants of the multidimensional architecture of intelligent systems components, which includes intercomponent knowledge flows and processes of knowledge synthesis within components, as well as invariants of control agents for abstract knowledge flows and processes within intelligent systems. The intelligent system knowledge base is presented as subject area ontology by non-ordered series of simple knowledge. Fragments of such ontology are distributed between components of intelligent systems three-dimensional architecture. The basis of such structure based on the dimensions of abstraction, structuring and the level of knowledge addressed to and processed within intelligent system's separate components. The ontologies reflect the ideas about the structures of memory and the processes of thinking used to model the schemes of the professional activity of a specialist. The basis for the formalization of such concepts is the fundamental principles of philosophy, linguistics, cognitive psychology, mathematics, and system engineering. This allows deploying a comprehensive system of classes of information structures and processes for complex knowledge synthesizing that support achievement of various cognitive goals implemented by specialists within professional tasks implementation processes. The goals system includes extraction, analysis and application of knowledge about user interfaces. The variety of such goals is modeled by a high-level implementation pattern system. They are composed of basic types of goals and are implemented using knowledge processing cognitive operations. Knowledge structures in the format of semantic hierarchies are used as a unified representation of knowledge. Cognitive goals are realized by combinations of operations on structured knowledge, adapted to special classes of structures.

Ontologies' Closures Modeling by Formalisms of Semantic Hierarchies

Schemes are studied for modeling the complex knowledge structures as synthesized from knowledge areas ontologies elements. These structures applications relate to knowledge life cycles and knowledge flows stages within intelligent systems. The format of semantic hierarchies is proposed as unified and universal for the synthesis of these structures. This allows replacing the general case of knowledge algebraic structures by special case of semantic hierarchies. Constructing the synthesized knowledge structures is performed by special operations knowledge alge­braic structures in any knowledge representation formalisms. These operations simulate fundamental mathematical systems functional aspects. They are adapted to the knowledge formalisms attributes. Attributes are explored within different knowledge areas. They associated generally with thinking operations and mind memory structure. Datasets (operations bases) of synthesis processes operations are constructed as special classes of knowledge with a uniform structure. Ontologies for considered knowledge areas are used as source of such bases constructing. Ontologies closures are defined as sets of knowledge that may be constructed off ontologies elements by synthesis operations. They determine the ontologies expressive capabilities. The constructs and operations over ontologies, that proposed at descriptive logics, can be modelled by knowledge complete structural representations, adopted for semantic hierarchies formalisms. Such formalisms are convenient for simulating knowledge presentation and processing. They form foundation for constructing intelligent systems abstract and applied models.. The possibility is proved for trans­ferring the knowledge properties and knowledge processing schemes at semantic hierarchies to the general case of knowledge algebraic structures. The schemes for modeling the ontological constructions as semantic hierarchies are given. This proves possibility of applying such formalisms as the basis for modeling synthesis processes in ontolo­gies. Such schemes allow constructing the ontologies closures as generated by knowledge-processing operations sequences. Last fact means possibility for formalisms of semantic hierarchies to be uniform foundation of modelling the knowledge flows and knowledge transforming processes by intelligent systems.

Finiteness in South Slavic Complement Clauses

This paper shows that the distribution of (non‑)finiteness in the South Slavic languages reflects an implicational scale along an independently attested semantic complementation hierarchy (e.g., Givón 1980). We suggest that in the South Slavic languages, finiteness is triggered by clausal agreement features associated with different syntactic heads. Building on a complexity approach to the complementation hierarchy, we propose that cross-linguistic variation in finiteness and variation across different types of complements are the result of language-specific differences in the distribution of agreement features. More broadly, we conclude that there is no (universal) semantic correlate of (non‑)finiteness and, contra cartographic approaches, that finiteness is not confined to a particular domain in the clause. Following Adger (2007), we argue that finiteness can be distributed over all clausal domains.

The Measurement of Chinese Sentence Semantic Complexity

The complexity of language is usually reflected in the complexity of sentences. At present, the research of sentence complexity mainly focuses on the analysis of syntactic complexity. In this paper, from the perspective of Leech's theory of sentence semantic structure, the predication structure is taken as the semantic unit to explore the sentence semantic complexity. The predication structures are extracted based on the result of sentence-based syntactic analysis, and then the linear expression sequence of a sentence is converted into a semantic hierarchy based on predicate semantic frameworks; the universality of predicate semantic frameworks is obtained by using the spectral clustering algorithm; and the sentence semantic complexity depends on the universality of predicate semantic frameworks at various layers. The experimental results show that the measurement method of sentence sematic complexity based on predicate semantic frameworks is more effective by comparing with the method that only considers the semantic categories of words in the sentence.

The position of object pronouns in the German middlefield

AbstractThis paper presents a corpus study of the position of object pronouns relative to a non-pronominal subject in embedded clauses of German. A total of 4322 embedded clauses from the deWaC corpus (Baroni, Marco, Silvia Bernardini, Adriano Ferraresi & Eros Zanchetta. 2009. The WaCky Wide Web: A collection of very large linguistically processed web-crawled corpora.Language Resources and Evaluation Journal23(3). 209–226), a corpus of written German Internet texts, were analyzed. In 67.0% of all clauses, the object pronoun occurred in front of the subject. Several factors that have been proposed in the literature on word order alternations were found to govern the choice between subject–object and object–subject order in the corpus under investigation. The most important findings are: (i) The Extended Animacy Hierarchy and the Semantic Role Hierarchy independently contribute to the choice of word order. (ii) The Definiteness Hierarchy has a strong effect on the position of the object pronoun. (iii) Word order effects of constituent weight, measured as length in number of words, cannot be reduced to effects of grammatical factors, nor can effects of grammatical factors be reduced to effects of weight.

The Application and Problem Analysis of Computer Technology in English Information Processing

The traditional method of automatic summarization is based on the statistical extraction of abstract sentences from the grammar, without semantic analysis of the text, resulting in low summarization accuracy. In order to overcome the shortcomings of traditional methods, this article proposes an automatic summarization method based on topic concepts. An English automatic summarization system is designed and implemented based on concept statistics and analytic hierarchy. Concept statistics replace traditional word frequency statistics, based on the main super The concept constructs a vector space model, calculates the importance of the sentence, selects the distribution of the main super concept on the concept hierarchy tree, analyzes the text structure and divides the meaning block, and extracts the abstract with the meaning block as the unit. Preliminarily solved the problem of unbalanced abstract structure of multi-topic articles. The experimental results show that through the methods of concept statistics and semantic hierarchy analysis, the abstracts generated by the English information processing system are more accurate and reflect the main content of the original text more comprehensively.