Hierarchical Semantic Structure Research Articles

Sensing the diversity of rumors: Rumor detection with hierarchical prototype contrastive learning

The proliferation of rumors on social networks poses a serious threat to cybersecurity, justice and public trust, increasing the urgent need for rumor detection. Existing detection methods typically treat all rumors as a single homogeneous category, neglecting the diverse semantic hierarchies within rumors. Rumors pervade various domains, each with its distinct characteristics. These methods tend to lag in expressiveness when confronted with real-world scenarios involving multiple semantic levels. Furthermore, the diversity of rumors also complicates the collection of datasets, and inevitably introduces noisy data, which hinders the correctness of the learned representations. To address these challenges, we propose a rumor detection framework with Hierarchical Prototype Contrastive Learning (HPCL). In this framework, we construct a set of dynamically updated hierarchical prototypes through contrastive learning to encourage capturing the hierarchical semantic structure within rumors. Additionally, we design a difficulty metric function based on the distance between instances and prototypes, and introduce curriculum learning to mitigate the adverse effects of noisy data. Experiments on four public datasets demonstrate that our approach achieves state-of-the-art performance. Our code is publicly released at https://github.com/Coder-HenryZa/HPCL.

Patch-Wise Graph Contrastive Learning for Image Translation

Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input image and the output image. To further explore the patch-wise topology for high-level semantic understanding, here we exploit the graph neural network to capture the topology-aware features. Specifically, we construct the graph based on the patch-wise similarity from a pretrained encoder, whose adjacency matrix is shared to enhance the consistency of patch-wise relation between the input and the output. Then, we obtain the node feature from the graph neural network, and enhance the correspondence between the nodes by increasing mutual information using the contrastive loss. In order to capture the hierarchical semantic structure, we further propose the graph pooling. Experimental results demonstrate the state-of-art results for the image translation thanks to the semantic encoding by the constructed graphs.

Hierarchical Perceptual Graph Attention Network for Knowledge Graph Completion

Knowledge graph completion (KGC), the process of predicting missing knowledge through known triples, is a primary focus of research in the field of knowledge graphs. As an important graph representation technique in deep learning, graph neural networks (GNNs) perform well in knowledge graph completion, but most existing graph neural network-based knowledge graph completion methods tend to aggregate neighborhood information directly and individually, ignoring the rich hierarchical semantic structure of KGs. As a result, how to effectively deal with multi-level complex relations is still not well resolved. In this study, we present a hierarchical knowledge graph completion technique that combines both relation-level and entity-level attention and incorporates a weight matrix to enhance the significance of the embedded information under different semantic conditions. Furthermore, it updates neighborhood information to the central entity using a hierarchical aggregation approach. The proposed model enhances the capacity to capture hierarchical semantic feature information and is adaptable to various scoring functions as decoders, thus yielding robust results. We conducted experiments on a public benchmark dataset and compared it with several state-of-the-art models, and the experimental results indicate that our proposed model outperforms existing models in several aspects, proving its superior performance and validating the effectiveness of the model.

Exploring Hierarchical Information in Hyperbolic Space for Self-Supervised Image Hashing.

In real-world datasets, visually related images often form clusters, and these clusters can be further grouped into larger categories with more general semantics. These inherent hierarchical structures can help capture the underlying distribution of data, making it easier to learn robust hash codes that lead to better retrieval performance. However, existing methods fail to make use of this hierarchical information, which in turn prevents the accurate preservation of relationships between data points in the learned hash codes, resulting in suboptimal performance. In this paper, our focus is on applying visual hierarchical information to self-supervised hash learning and addressing three key challenges, including the construction, embedding, and exploitation of visual hierarchies. We propose a new self-supervised hashing method named Hierarchical Hyperbolic Contrastive Hashing (HHCH), making breakthroughs in three aspects. First, we propose to embed continuous hash codes into hyperbolic space for accurate semantic expression since embedding hierarchies in the hyperbolic space generates less distortion than in the hyper-sphere or Euclidean space. Second, we update the K-Means algorithm to make it run in the hyperbolic space. The proposed hierarchical hyperbolic K-Means algorithm can achieve the adaptive construction of hierarchical semantic structures. Last but not least, to exploit the hierarchical semantic structures in hyperbolic space, we propose the hierarchical contrastive learning algorithm, including hierarchical instance-wise and hierarchical prototype-wise contrastive learning. Extensive experiments on four benchmark datasets demonstrate that the proposed method outperforms state-of-the-art self-supervised hashing methods. Our codes are released at https://github.com/HUST-IDSM-AI/HHCH.git.

Unraveling lexical semantics in the brain: Comparing internal, external, and hybrid language models.

To explain how the human brain represents and organizes meaning, many theoretical and computational language models have been proposed over the years, varying in their underlying computational principles and in the language samples based on which they are built. However, how well they capture the neural encoding of lexical semantics remains elusive. We used representational similarity analysis (RSA) to evaluate to what extent three models of different types explained neural responses elicited by word stimuli: an External corpus-based word2vec model, an Internal free word association model, and a Hybrid ConceptNet model. Semantic networks were constructed using word relations computed in the three models and experimental stimuli were selected through a community detection procedure. The similarity patterns between language models and neural responses were compared at the community, exemplar, and word node levels to probe the potential hierarchical semantic structure. We found that semantic relations computed with the Internal model provided the closest approximation to the patterns of neural activation, whereas the External model did not capture neural responses as well. Compared with the exemplar and the node levels, community-level RSA demonstrated the broadest involvement of brain regions, engaging areas critical for semantic processing, including the angular gyrus, superior frontal gyrus and a large portion of the anterior temporal lobe. The findings highlight the multidimensional semantic organization in the brain which is better captured by Internal models sensitive to multiple modalities such as word association compared with External models trained on text corpora.

Hierarchical Semantic Structure Preserving Hashing for Cross-Modal Retrieval

Cross-modal hashing has become a vital technique in cross-modal retrieval due to its fast query speed and low storage cost in recent years. Generally, most of the priors supervised cross-modal hashing methods are flat methods which are designed for non-hierarchical labeled data. They treat different categories independently and ignore the inter-category correlations. In practical applications, many instances are labeled with hierarchical categories. The hierarchical label structure provides rich information among different categories. To rationally take use of category correlations, hierarchical cross-modal hashing is proposed. However, existing methods intend to preserve instance-pairwise or class-pairwise similarities, which cannot fully explore the semantic correlations among different categories and make the learned hash codes less discriminative. In this paper, we propose a deep cross-modal hashing method named hierarchical semantic structure preserving hashing (HSSPH), which directly exploits the label hierarchy information to learn discriminative hash codes. Specifically, HSSPH learns a set of class-wise hash codes for each layer. By augmenting class-wise codes with labels, it generates layer-wise prototype codes which reflect the semantic structure of each layer. In order to enhance the discriminative ability of hash codes, HSSPH supervises the hash codes learning with both labels and semantic structures to preserve the hierarchical semantics. Besides, efficient optimization algorithms are developed to directly learn the discrete hash codes for each instance and each class. Extensive experiments on two benchmark datasets show the superiority of HSSPH over several state-of-the-art methods.

Hierarchical state recurrent neural network for social emotion ranking

Text generation with auxiliary attributes, such as topics or sentiments, has made remarkable progress. However, high-quality labeled data is difficult to obtain for the large-scale corpus. Therefore, this paper focuses on social emotion ranking aiming to identify social emotions with different intensities evoked by online documents, which could be potentially beneficial for further controlled text generation. Existing studies often consider each document as an entirety that fail to capture the inner relationship between sentences in a document. In this paper, we propose a novel hierarchical state recurrent neural network for social emotion ranking. A hierarchy mechanism is employed to capture the key hierarchical semantic structure in a document. Moreover, instead of incrementally reading a sequence of words or sentences as in traditional recurrent neural networks, the proposed approach encodes the hidden states of all words or sentences simultaneously at each recurrent step to capture long-range dependencies precisely. Experimental results show that the proposed approach performs remarkably better than the state-of-the-art social emotion ranking approaches and is useful for controlled text generation.

Detecting Communities with Multiplex Semantics by Distinguishing Background, General, and Specialized Topics

Finding semantic communities using network topology and contents together is a hot topic in community detection. Existing methods often use word attributes in an indiscriminate way to help finding communities. Through analysis we find that, words in networked contents often embody a hierarchical semantic structure. Some words reflect a background topic of the whole network with all communities, some imply the high-level general topic covering several topic-related communities, and some imply the high-resolution specialized topic to describe each community. Ignoring such semantic structures often leads to defects in depicting networked contents where deep semantics are not fully utilized. To solve this problem, we propose a new Bayesian probabilistic model. By distinguishing words from either a background topic or some two-level topics (i.e., general and specialized topics), this model not only better utilizes the networked contents to help finding communities, but also provides a clearer multiplex semantic community interpretation. We then give an efficient variational algorithm for model inference. The superiority of this new approach is demonstrated by comparing with ten state-of-the-art methods on nine real networks and an artificial benchmark. A case study is further provided to show its strong ability in deep semantic interpretation of communities.

Grounding of Modal Responses in Question Answering System Equipped with Hierarchical Categorisation

Intelligent and dialogue systems highly utilise natural language interfaces. Such systems do not only process linguistic questions, but also formulate proper linguistic responses. Often neglected and important aspect of such responses lies in the ability to express and communicate systems internal beliefs. The proposed model fills in the current research gap in the grounding theory by enriching empirical experiences with hierarchical semantic structures in establishing agents internal belief stance. Such an extension significantly influences the process of grounding and allows for a dedicated computational mechanism of moving the conversations focus, which is incorporated into grounding mechanisms and fully presented.

Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics

Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zero-shot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot fine-grained classification.

Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations

The research presents the methodology of improving the accuracy in sentiment classification in the light of modelling the latent semantic relations (LSR). The objective of this methodology is to find ways of eliminating the limitations of the discriminant and probabilistic methods for LSR revealing and customizing the sentiment classification process (SCP) to the more accurate recognition of text tonality. This objective was achieved by providing the possibility of the joint usage of the following methods: (1) retrieval and recognition of the hierarchical semantic structure of the text and (2) development of the hierarchical contextually-oriented sentiment dictionary in order to perform the context-sensitive SCP. The main scientific contribution of this research is the set of the following approaches: at the phase of LSR revealing (1) combination of the discriminant and probabilistic models while applying the rules of adjustments to obtain the final joint result; at all SCP phases (2) considering document as a complex structure of topically completed textual components (paragraphs) and (3) taking into account the features of persuasive documents’ type. The experimental results have demonstrated the enhancement of the SCP accuracy, namely significant increase of average values of recall and precision indicators and guarantee of sufficient accuracy level.

Hierarchical Semantic Mapping Using Convolutional Neural Networks for Intelligent Service Robotics

The introduction of service robots in the public domain has introduced a paradigm shift in how robots are interacting with people, where robots must learn to autonomously interact with the untrained public instead of being directed by trained personnel. As an example, a hospital service robot is told to deliver medicine to Patient Two in Ward Three. Without awareness of what “Patient Two” or “Ward Three” is, a service robot must systematically explore the environment to perform this task, which requires a long time. The implementation of a Semantic Map allows for robots to perceive the environment similar to people by associating semantic information with spatial information found in geometric maps. Currently, many semantic mapping works provide insufficient or incorrect semantic-metric information to allow a service robot to function dynamically in human-centric environments. This paper proposes a semantic map with a hierarchical semantic organization structure based on a hybrid metric-topological map leveraging convolutional neural networks and spatial room segmentation methods. Our results are validated using multiple simulated and real environments on our lab’s custom developed mobile service robot and demonstrate an application of semantic maps by providing only vocal commands. We show that this proposed method provides better capabilities in terms of semantic map labeling and retain multiple levels of semantic information.

Automatic hierarchical mid-surface abstraction of thin-walled model based on rib decomposition

Model simplification is imperative in the process of computer aided design (CAD) and computer aided engineering (CAE) integration. Mid-surface abstraction is the most effective method to simplify the thin-walled models. Many previous research efforts have been focused on the mid-surface abstraction, including the model decomposition based methods, Medial Axis Transform (MAT) based methods and Chordal Axis Transform (CAT) based methods. However, complex thin-walled models cannot be handled well due to the fact that there are some problems including low geometrical precision, poor topological structure, etc., in the above resultant mid-surface models. Especially, these methods are hard to be reused to generate the mid-surface model efficiently. Therefore, a hierarchical semantic mid-surface abstraction method is proposed for the thin-walled model based on rib feature decomposition in this paper. Firstly, a new hierarchical semantic structure is defined and applied on both the thin-walled models and mid-surface models. After that, the model decomposition is conducted based on the identified rib features and the hierarchical semantic information is obtained at the same time. Then, the offset operation and discretization based methods are used to obtain the mid-surface patch for each sub region with different semantic structure respectively. Finally, the mid-surface model with hierarchical semantic information is generated by stitching all discrete patches. Moreover, the above model can be reused to facilitate the rapid mid-surface abstraction of the changed model based on its hierarchical semantic structure. Several examples are given to demonstrate the outperformance of the proposed method.

The hierarchical semantic structure of respect-related emotions in modern Japanese people

This study examined the reproducibility of the hierarchical semantic structure of respect-related emotions and the prototypical meaning of sonkei (respect) in modern Japanese people. Participants, ages 20-79, rated the semantic similarity of 153 pairs of 18 respect-related words used in previously published work. Hierarchical cluster analysis (n = 515) showed almost the same semantic organization as the previous study. The highest level of abstraction consisted of "person-focus respect, emotional attitude" and "action-focus respect, emotional state." The basic-level consisted of (a) respect mingled with mild love; (b) ought-respect (respect as moral duty); (c) idolatry (worship and adoration); (d) awe mingled with fear; (e) admiration; and (f) wonder. The word sonkei was included in category (a). Additional analyses were conducted according to age. The results revealed that the basic categories seen in adults ages 60-79 differed from those in the whole sample and that sonkei was included in the category which could be considered as, ought-respect. These findings suggest that the semantic organization of respect-related emotions is gradually changing under the influence of modern culture.

Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach

Feature representation learning is an important and fundamental task in multimedia and pattern recognition research. In this paper, we propose a novel framework to explore the hierarchical structure inside the images from the perspective of feature representation learning, which is applied to hierarchical image annotation. Different from the current trend in multimedia analysis of using pre-defined features or focusing on the end-task flat representation, we propose a novel layer-wise tag-embedded deep learning (LTDL) model to learn hierarchical features which correspond to hierarchical semantic structures in the tag hierarchy. Unlike most existing deep learning models, LTDL utilizes both the visual content of the image and the hierarchical information of associated social tags. In the training stage, the two kinds of information are fused in a bottom-up way. Supervised training and multi-modal fusion alternate in a layer-wise way to learn feature hierarchies. To validate the effectiveness of LTDL, we conduct extensive experiments for hierarchical image annotation on a large-scale public dataset. Experimental results show that the proposed LTDL can learn representative features with improved performances.

Hierarchical semantic structures for medical NLP.

We present a framework for building a medical natural language processing (NLP) system capable of deep understanding of clinical text reports. The framework helps developers understand how various NLP-related efforts and knowledge sources can be integrated. The aspects considered include: 1) computational issues dealing with defining layers of intermediate semantic structures to reduce the dimensionality of the NLP problem; 2) algorithmic issues in which we survey the NLP literature and discuss state-of-the-art procedures used to map between various levels of the hierarchy; and 3) implementation issues to software developers with available resources. The objective of this poster is to educate readers to the various levels of semantic representation (e.g., word level concepts, ontological concepts, logical relations, logical frames, discourse structures, etc.). The poster presents an architecture for which diverse efforts and resources in medical NLP can be integrated in a principled way.

A Graph-Partitioning Framework for Aligning Hierarchical Topic Structures to Presentations

This paper studies the problem of imposing an existing hierarchical semantic structure onto a corresponding spoken document in which the structures are embedded, with the goal of indexing such documents for easier access. We propose a graph-partitioning framework to solve a semantic tree-to-string alignment problem through optimizing a normalized-cut criterion. We present models with different modeling capabilities and time complexities in this framework and provide experimental evidence of their performance. We relate graph partitioning to conventional dynamic time warping (DTW) as it applies to this problem, and show that the proposed framework can naturally include topic segmentation to accommodate cohesion constraints.

A Semantic Concept Operation Based on Fuzzy Document Ordering System and its Application to Reuter Database

A fuzzy document ordering system (FOCUS) with a shrink operation is proposed to classify vast unknown documents on the Worldwide Web by changing the user’s viewpoint in hierarchical semantic concept structures. The shrink operation, a FOCUS semantic concept, is defined based on the user’s preference vector space and its hierarchical semantic concept structures developed using the concept System Dictionary (CSD) of the Japan Electronic Dictionary Research Institute (EDR). We demonstrate the effectiveness of the shrink operation in document ordering experiments by 5 subjects a using 20 known and 40 unknown documents extracted from the Reuter-21578 Database, i.e., shrinkage of the user’s preference vector space. We confirmed that precision obtained by FOCUS with the shrink operation exceeds that obtained by the conventional method without the shrink operation by over 20%. Processing time by our proposal is just 1/18 that of the conventional method (Pentium III, 550 MHz, Memory 256 MB).

Umiejętność odtwarzania hierarchii typu hiponimicznego przez niewidomych i widzących użytkowników języka

The ability to reconstruct hierarchical semantic structures by blind and sighted average language users. The present paper concerns the hierarchically organised semantic structure of the mental lexicon. The structure of hierarchical series of nouns constructed for 75 Polish nouns by 116 subjects (58 blind and 58 sighted) was analysed and compared.

OntoMiner: automated metadata and instance mining from news websites

RDF/XML has been widely recognised as the standard for annotating online web documents and for transforming the HTML web into the so-called Semantic Web. In order to enable widespread usability of the Semantic Web, there is a need to bootstrap large, rich and up-to-date domain ontologies that organise the most relevant concepts, their relationships and instances. In this paper, we present automated techniques for bootstrapping and populating specialised domain ontologies by organising and mining a set of relevant overlapping websites. We develop algorithms that detect and utilise HTML regularities in the web documents to turn them into hierarchical semantic structures encoded as XML. Next, we present tree-mining algorithms that identify key domain concepts and their taxonomical relationships. We also extract semi-structured concept instances annotated with their labels whenever they are available. We also report experimental evaluation for the news, travel and shopping domains to demonstrate the efficacy of our algorithms.