Representation Of Relations Research Articles

A multi-view representation learning framework for commonsense knowledge bases

Commonsense knowledge bases play an essential role in a wide range of natural language processing tasks. This paper studies the problem of representation learning for commonsense knowledge bases to effectively incorporate their knowledge into numerical models. Most existing knowledge base representation learning methods are difficult to apply to commonsense knowledge bases since they are much sparser than general knowledge bases. Hence, in this paper, we propose a novel method for commonsense knowledge base representation learning. Specifically, we first model the nodes from multiple views, including word/phase information, context information, and graph information. Then, we design a scoring function to measure whether the commonsense triplets are established through relation representation learning. We conduct extensive experiments on two tasks and the results show that our proposed model outperforms other knowledge base representation learning methods.

Mechanism and Application of Attitude and Orbit Coupling Dynamics for Spacecraft Proximity Relative Motion

This paper analyzes the root causes of attitude-orbit coupling effects of spacecraft proximity relative motion in space precision collaborative tasks from three aspects: mathematical representation, physical definition, and engineering applications. At first, taking mathematical representation as the context, spacecraft proximity relative motion representations such as particle relative dynamic model, extended particle relative dynamic model, and dual-spiral-based relative dynamic model are investigated in detail. On this basis, the mechanism of attitude-orbit coupling effects originating from different mathematical representations is further investigated. Second, spiral theory–based attitude-orbit coupling relative dynamics is developed. The innovation of this work is extending the dual number representation from rigid body to flexible body, which makes it possible to describe the proximity relative motion between two rigid-flexible coupling spacecraft. Third, the application value of attitude-orbit coupling relative dynamic model in precision collaborative mission such as precision formation, rendezvous and docking, space manipulation, and on-orbit assembly is provided. Finally, simulation results verify the engineering significance of the attitude-orbit coupling relative dynamic model.

Relation-aware heterogeneous graph neural network for entity alignment

Entity alignment refers to finding equivalent entities from different knowledge graphs. Most of the existing entity alignment methods are studied based on homogeneous graphs. However, the knowledge graph is a heterogeneous graph containing many types of nodes, such as entities, relations, and attributes. Therefore, we propose introducing a heterogeneous graph neural network to model entities and relations simultaneously and propose an iterative fusion method to enhance the interaction between these two semantic nodes. Since not all datasets contain relation information, this paper does not directly introduce a feature representation of relations. The generalizability of the approach is improved by utilizing a relation-aware strategy to obtain information about the relation. Specifically, the information propagation of the head and tail entities in the triplet is utilized to obtain the feature representation of the relation. Experimental results show that the present method performs better on three cross-lingual datasets DBP15K and two large-scale datasets DWY100K.

United as one? Personal and social identity threats differentially predict cooperation and prejudice toward minorities

ABSTRACT Global threats are often identified as triggers of intergroup conflict. However, personal vs. social identity threats can differently shape intergroup relations – enhancing or decreasing cooperation and prejudice. We tested the idea that appraisals of different types of threat (to personal vs. social identity motives) shape specific representations of intergroup relations (as one-group recategorization or separate-group coalition), which have opposing implications for modern prejudice toward ethnic minorities. In four studies (N = 2,772) performed in the context of the COVID-19 pandemic, we found evidence that personal threats were negatively associated with modern prejudice and this relation was mediated by preferences for separate group-representations, whereas social identity threats were positively associated with modern prejudice and mediated by preferences for one group representations.

Bakom den leende masken


 Theme: Motherhood and Mothering. Ill. ©Stina Wirsén
 Behind the Pretty Mask: Vulnerable Mothering in Contemporary Picturebooks about Surrogacy and Illness
 Children and adults, the dual audience of picturebooks, are joined in the act of reading aloud. For many parents, reading to their child constitutes one of the basic, intimate care practices of mothering (Rich; Holm). In this study, we examine picturebooks about surrogacy and about mothering parents who are mentally or physically ill, published in Sweden in the period between 2010 and 2022. Both types of books depict a vulnerability in relation to parenthood, motherhood and mothering and are often autobiographical and niche- or self-published. With an analytical approach grounded in critical theories of adult agency in children’s literature (Rose; Nodelman; Beauvais), we find that both picturebooks about surrogacy and illness communicate straightforward and often sentimental messages to the child reader, whereas more complex and possibly problematic adult desires and needs can be detected on the level of the adult address. Through the projected child perspective (Rhedin), our material offers the vulnerable adult reader representation and recognition in relation to a motherhood/mothering that is not unequivocally considered sufficient or legitimate. The traditional aesthetics and pedagogical use-value of the picturebook as well as the positive maternal associations to reading aloud, are essential in this legitimization process. Meanwhile, the implied child reader functions as a projection surface for adult wishes of normalcy and happy endings. Although hidden behind adult projections, it is this “mighty” child (Beauvais) who ultimately has the power to acknowledge and justify the parents in an impending future which reaches beyond the control of both adult writer and implied adult reader.

On Higher-Order Generalized Fibonacci Hybrinomials: New Properties, Recurrence Relations and Matrix Representations

This paper presents a comprehensive survey of the generalization of hybrid numbers and hybrid polynomials, particularly in the fields of mathematics and physics. In this paper, by using higher-order generalized Fibonacci polynomials, we introduce higher-order generalized Fibonacci hybrid polynomials called higher-order generalized Fibonacci hybrinomials. We obtain some special cases and algebraic properties of the higher-order generalized Fibonacci hybrinomials, such as the recurrence relation, generating function, exponential generating function, Binet formula, Vajda’s identity, Catalan’s identity, Cassini’s identity and d’Ocagne’s identity. We also present three different matrices whose components are higher-order generalized Fibonacci hybrinomials, higher-order generalized Fibonacci polynomials and Lucas polynomials. By using these matrices, we obtain some identities related to these newly established hybrinomials.

RiQ-KGC: Relation Instantiation Enhanced Quaternionic Attention for Complex-Relation Knowledge Graph Completion

A knowledge graph is a structured semantic network designed to describe physical entities and relations in the world. A comprehensive and accurate knowledge graph is essential for tasks such as knowledge inference and recommendation systems, making link prediction a popular problem for knowledge graph completion. However, existing approaches struggle to model complex relations among entities, which severely hampers their ability to complete knowledge graphs effectively. To address this challenge, we propose a novel hierarchical multi-head attention network embedding framework, called RiQ-KGC, which integrates different-grained contextual information of knowledge graph triples and models quaternion rotation relations between entities. Furthermore, we propose a relation instantiation method for alleviating the difficulty of expressing complex relations between entities. To enhance the expressiveness of relation representation, the relation is integrated by Transformer to obtain multi-hop neighbor information, so that one relation can be embedded into different embeddings according to different entities. Experimental results on four datasets demonstrate that RiQ-KGC exhibits strong competitiveness compared to state-of-the-art models in link prediction, while the ablation experiments reveal that the proposed relation instantiation method achieves great performance.

Relation representation based on private and shared features for adaptive few-shot link prediction

Relation representation based on private and shared features for adaptive few-shot link prediction

Who notices Gymnophiona? Google Trends data reveal interesting trends for recent amphibian species

Gymnophiona (caecilians) are inconspicuous, wormlike amphibians that are often hidden from human sight due to their aquatic or fossorial lifestyles. While Google Trends data have been widely used within conservation biology to provide information about the relative interest in species, and therefore of their flagship-making potential, as well as to identify current taxonomic biases. This study aimed to evaluate public interest in amphibians, with a particular focus on caecilians, and possible taxonomic biases of and within the class Amphibia. Google Trends data from amphibians, reptiles (sauropsids, excluding aves), and fishes (chondrichthyans + osteichthyans, excluding tetrapods) were analyzed and compared. In addition, a framework for a representation index and web representation index is presented. The introduced relative representation index was able to confirm taxonomic bias concerning Amphibia. Differences in worldwide public interest could also be evaluated within amphibians, indicating severe underrepresentation in public interest for caecilians.

Self-supervised commonsense knowledge learning for document-level relation extraction

Compared to sentence-level relation extraction, practical document-level relation extraction (DocRE) is a more challenging task for which multi-entity problems need to be resolved. It aims at extracting relationships between two entities over multiple sentences at once while taking into account significant cross-sentence features. Learning long-distance semantic relation representation across sentences in a document, however, is a widespread and difficult task. To address the above issues, we propose a novel Self-supervised Commonsense-enhanced DocRE approach, named as SCDRE, bypassing the need for external knowledge. The methodology begins by harnessing self-supervised learning to capture the commonsense knowledge pertaining to each entity within an entity pair, drawing insights from the commonsense entailed text. This acquired knowledge subsequently serves as the foundation for transforming cross-sentence entity pairs into alias counterparts achieved by the coreference commonsense replacement. The focus then shifts to semantic relation representation learning, applied to these alias entity pairs. Through a process of entity pair rich attention fusion, these alias pairs are seamlessly and automatically translated back into the target entity pairs. This innovation harnesses self-supervised learning and contextual commonsense to distinguish SCDRE as a unique and self-contained approach, promising an enhanced ability to extract relationships from documents. We examine our model on three publicly accessible datasets, DocRED, DialogRE and MPDD, and the results show that it performs significantly better than strong baselines by 2.03% F1, and commonsense knowledge has an important contribution to the DocRE by the ablation experimental analysis.

‘All true histories contain instruction’: Truth and Everyday Heroism in Agnes Grey

The writings of the Brontës have frequently been studied in relation to conceptions of heroism. More specifically, critics have focused on the influence of war heroes such as the Duke of Wellington or Napoleon in the early writings of the siblings, principally those authored by Charlotte and Branwell Brontë. This article, however, explores the conception of ‘everyday heroism’ in Anne Brontë’s novel Agnes Grey (1847). It argues that the ordinary characters portrayed in Brontë’s work embody qualities usually associated with the heroic. Further, the analysis of heroism can reveal new insights into the representation of gender roles and class relations in the novel.

HEDV-Greedy: An Advanced Algorithm for Influence Maximization in Hypergraphs

Influence maximization (IM) has shown wide applicability in various fields over the past few decades, e.g., viral marketing, rumor control, and prevention of infectious diseases. Nevertheless, existing research on IM primarily focuses on ordinary networks with pairwise connections between nodes, which fall short in the representation of higher-order relations. Influence maximization on hypergraphs (HIM) has received limited research attention. A novel evaluation function, which aims to evaluate the spreading influence of selected nodes on hypergraphs, i.e., expected diffusion value on hypergraph (HEDV), is proposed in this work. Then, an advanced greedy-based algorithm, termed HEDV-greedy, is proposed to select seed nodes with maximum spreading influence on the hypergraph. We conduct extensive experiments on eight real-world hypergraph datasets, benchmarking HEDV-greedy against eight state-of-the-art methods for the HIM problem. Extensive experiments conducted on real-world datasets highlight the effectiveness and efficiency of our proposed methods. The HEDV-greedy algorithm demonstrates a marked reduction in time complexity by two orders of magnitude compared to the conventional greedy method. Moreover, HEDV-greedy outperforms other state-of-the-art algorithms across all datasets. Specifically, under conditions of lower propagation probability, HEDV-greedy exhibits an average improvement in solution accuracy of 25.76%.

Student mental health support: A qualitative evaluation of new well-being services at a UK university

ABSTRACT Increasing numbers of UK students now seek mental health support while at university. Clear evidence for the best configuration of student support services is lacking. Most service evaluations have focused on counselling – with little evaluation of low-intensity support services such as non-clinical mental health and well-being teams or student accommodation welfare support. This qualitative study addresses that gap, examining student and staff experiences of new well-being advisers in academic departments and halls of residence at one UK university in 2018, marking a step-change in welfare support delivery. Using reflexive thematic analysis with data collected in 40 focus groups and interviews approximately 18 months after service launch, five themes were identified: Trusted Friend; Joined Up Approach; Proactive versus Reactive; Belonging; and My University Cares. The well-being advisers offered timely, low-intensity support as an accessible, approachable addition to academic, clinical and online provision. However, evidence showed operational challenges such as data-sharing between academic, professional and support service staff. The volume of students seeking support also appeared to compromise resource intended for preventative and community-building work, particularly in student accommodation. Concerns remained for students who do not seek help, with findings underlining the importance of issues of belonging, connection and representation in relation to well-being support. Notably, this highly visible well-being investment appeared to shift a negative cultural narrative which was undermining student and staff confidence to one of greater reassurance of support. Our conclusions have implications for student support service configuration and emphasise the importance of a whole university well-being approach.

Excursus on modulation spaces via metaplectic operators and related time-frequency representations

We provide a comprehensive overview of the theoretical framework surrounding modulation spaces and their characterizations, particularly focusing on the role of metaplectic operators and time-frequency representations. We highlight the metaplectic action which is hidden in their construction and guarantees equivalent (quasi-)norms for such spaces. In particular, this work provides new characterizations via the submanifold of shift-invertible symplectic matrices. Similar results hold for the Wiener amalgam spaces.

Enhancing Low-Resource Relation Representations through Multi-View Decoupling

Recently, prompt-tuning with pre-trained language models (PLMs) has demonstrated the significantly enhancing ability of relation extraction (RE) tasks. However, in low-resource scenarios, where the available training data is scarce, previous prompt-based methods may still perform poorly for prompt-based representation learning due to a superficial understanding of the relation. To this end, we highlight the importance of learning high-quality relation representation in low-resource scenarios for RE, and propose a novel prompt-based relation representation method, named MVRE (Multi-View Relation Extraction), to better leverage the capacity of PLMs to improve the performance of RE within the low-resource prompt-tuning paradigm. Specifically, MVRE decouples each relation into different perspectives to encompass multi-view relation representations for maximizing the likelihood during relation inference. Furthermore, we also design a Global-Local loss and a Dynamic-Initialization method for better alignment of the multi-view relation-representing virtual words, containing the semantics of relation labels during the optimization learning process and initialization. Extensive experiments on three benchmark datasets show that our method can achieve state-of-the-art in low-resource settings.

RedCore: Relative Advantage Aware Cross-Modal Representation Learning for Missing Modalities with Imbalanced Missing Rates

Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest. In this paper, we investigate two challenging problems: 1) when modality missing exists in the training data, how to exploit the incomplete samples while guaranteeing that they are properly supervised? 2) when the missing rates of different modalities vary, causing or exacerbating the imbalance among modalities, how to address the imbalance and ensure all modalities are well-trained. To tackle these two challenges, we first introduce the variational information bottleneck (VIB) method for the cross-modal representation learning of missing modalities, which capitalizes on the available modalities and the labels as supervision. Then, accounting for the imbalanced missing rates, we define relative advantage to quantify the advantage of each modality over others. Accordingly, a bi-level optimization problem is formulated to adaptively regulate the supervision of all modalities during training. As a whole, the proposed approach features Relative advantage aware Cross-modal representation learning (abbreviated as RedCore) for missing modalities with imbalanced missing rates. Extensive empirical results demonstrate that RedCore outperforms competing models in that it exhibits superior robustness against either large or imbalanced missing rates. The code is available at: https://github.com/sunjunaimer/RedCore.

Dependency Structure-Enhanced Graph Attention Networks for Event Detection

Existing models on event detection share three-fold limitations, including (1) insufficient consideration of the structures between dependency relations, (2) limited exploration of the directed-edge semantics, and (3) issues in strengthening the event core arguments. To tackle these problems, we propose a dependency structure-enhanced event detection framework. In addition to the traditional token dependency parsing tree, denoted as TDG, our model considers the dependency edges in it as new nodes and constructs a dependency relation graph (DRG). DRG allows the embedding representations of dependency relations to be updated as nodes rather than edges in a graph neural network. Moreover, the levels of core argument nodes in the two graphs are adjusted by dependency relation types in TDG to enhance their status. Subsequently, the two graphs are further encoded and jointly trained in graph attention networks (GAT). Importantly, we design an interaction strategy of node embedding for the two graphs and refine the attention coefficient computational method to encode the semantic meaning of directed edges. Extensive experiments are conducted to validate the effectiveness of our method, and the results confirm its superiority over the state-of-the-art baselines. Our model outperforms the best benchmark with the F1 score increased by 3.5 and 3.4 percentage points on ACE2005 English and Chinese corpus.

Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-Modal Structured Representations

Large-scale vision-language pre-training has achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require structured representations, i.e., representations of objects, attributes, and relations. The models cannot make a distinction between "An astronaut rides a horse" and "A horse rides an astronaut". This is because they fail to fully leverage structured knowledge when learning multi-modal representations. In this paper, we present an end-to-end framework Structure-CLIP, which integrates Scene Graph Knowledge (SGK) to enhance multi-modal structured representations. Firstly, we use scene graphs to guide the construction of semantic negative examples, which results in an increased emphasis on learning structured representations. Moreover, a Knowledge-Enhance Encoder (KEE) is proposed to leverage SGK as input to further enhance structured representations. To verify the effectiveness of the proposed framework, we pre-train our model with the aforementioned approaches and conduct experiments on downstream tasks. Experimental results demonstrate that Structure-CLIP achieves state-of-the-art (SOTA) performance on VG-Attribution and VG-Relation datasets, with 12.5% and 4.1% ahead of the multi-modal SOTA model respectively. Meanwhile, the results on MSCOCO indicate that Structure-CLIP significantly enhances the structured representations while maintaining the ability of general representations. Our code is available at https://github.com/zjukg/Structure-CLIP.

The Tenement House in the City. Depictions of a multi-ethnic neighbourhood inselected Polish interwar novels

The article analyses literary representations of relations between the inhabitants of tenement houseswho belong to different ethnic groups. Selected interwar novels by Henryk Drzewiecki, HalinaGórska, Marcelina Grabowska, Władysław Pawlak, and Andrzej Strug are discussed as literary insightsinto historical and social conditions of the neighbourly coexistence of ethnically mixed communities.

Entity alignment with fusing relation representation

Entity alignment is the task of identifying entities from different knowledge graphs (KGs) that point to the same item and is important for KG fusion. In the real world, due to the heterogeneity between different KGs, equivalent entities often have different relations around them, so it is difficult for Graph Convolutional Network (GCN) to accurately learn the relation information in the KGs. Moreover, to solve the problem regarding inadequate utilisation of relation information in entity alignment, a novel GCN-based model, joint Unsupervised Relation Alignment for Entity Alignment (URAEA), is proposed. The model first employs a novel method for calculating relation embeddings by using entity embeddings, then constructs unsupervised seed relation alignments through these relation embeddings, and finally performs entity alignment together with relation alignment. In addition, the seed entity alignments are expanded based on the generated seed relation alignments. Experiments conducted on three real-world datasets show that this approach outperforms state-of-the-art methods.