Matching Entities Research Articles

Research on 3D geographic entity recognition method based on the double matching degree

Abstract In the process of real-view 3D construction, the description of the same geospatial object by multiple departments is not the same, and how to link the city’s multi-source datasets to the same entity and construct the mapping relationship between multi-source data has become the current difficulty of multi-source data convergence. A double-matching degree entity recognition method was proposed in this paper for the problem of unified geographic entities in data convergence. Firstly, the address information is extracted from the original address data according to the address elements, and the hierarchical address tree is established by using the organization of a dictionary tree for hierarchical matching. The BERT model and twin neural network are introduced to divide the address information on the remaining paths at the byte and word level to calculate the similarity of address information. Then, the similarity of entity names is calculated by the method based on editing distance, and by combining the string-based method and the neural network-based method with each other, the hierarchical step-by-step matching is performed to narrow the matching space, determine the matching entities, and establish the entity links. Experiments on the self-built dataset show that this method has performed better in entity recognition compared to other methods.

A semi-supervised framework fusing multiple information for knowledge graph entity alignment

Entity alignment (EA) is a fundamental task for cross linguistic knowledge graphs (KGs) understanding and interaction, which is committed to matching entities from different graphs based on their inherent semantics. Methods based on graph neural networks (GNNs) dominate the EA task, however, the majority of them ignore the higher-order information among entities in the KGs. Meanwhile, as important auxiliary information, the relational semantics, string information of entity names and attribute information of entities are insufficiently exploited during the inference phase. In addition, labeled alignment data is universally insufficient across various datasets, which limits the performance of the model. In this paper, we propose a Semi-supervised EA framework that Comprehensively considers both Structural and Attribute information within KGs (SCSA) to address these problems above. Specifically, our approach first leverages hypergraph neural networks (HGNN) to aggregate relational semantic information and graph convolutional networks (GCNs) with a highway filtering strategy to acquire the embedding representation of entities precisely. Then, we propose a bidirectional filtering technique with a combination of entity, attribute and string values to create pseudo-labeled data and lead the model for iteratively training. We implement our proposed framework on several publicly recognized cross-lingual datasets. The experimental results indicate that our framework outperforms almost all state-of-the-art (SOTA) methods.

A self-supervised entity alignment framework via attribute correction

Entity alignment (EA), aiming to match entities with the same meaning across different knowledge graphs (KGs), is a critical step in knowledge fusion. Existing EA methods usually encode the multi-aspect features of entities as embeddings and learn to align the embeddings with supervised learning. Although these methods have achieved remarkable results, two issues have not been well addressed. Firstly, these methods require pre-aligned entity pairs to perform EA tasks, limiting their applicability in practice. Secondly, these methods overlook the unique contribution of digital attributes to EA tasks when utilising attribute information to enhance entity features. In this paper, we propose a self-supervised entity alignment framework via attribute correction. Specifically, we first design a highly effective seed pair generator based on multi-aspect features of entities to solve the labour-intensive problem of obtaining pre-aligned entity pairs. Then, a novel alignment mechanism via attribute correction is proposed to address the problem that different types of attributes have different contributions to the EA task. Extensive experiments on real-world datasets with semantic features demonstrate that our framework outperforms state-of-the-art (SOTA) EA tasks.

Triplet-aware graph neural networks for factorized multi-modal knowledge graph entity alignment

Multi-Modal Entity Alignment (MMEA), aiming to discover matching entity pairs on two multi-modal knowledge graphs (MMKGs), is an essential task in knowledge graph fusion. Through mining feature information of MMKGs, entities are aligned to tackle the issue that an MMKG is incapable of effective integration. The recent attempt at neighbors and attribute fusion mainly focuses on aggregating multi-modal attributes, neglecting the structure effect with multi-modal attributes for entity alignment. This paper proposes an innovative approach, namely TriFac, to exploit embedding refinement for factorizing the original multi-modal knowledge graphs through a two-stage MMKG factorization. Notably, we propose triplet-aware graph neural networks to aggregate multi-relational features. We propose multi-modal fusion for aggregating multiple features and design three novel metrics to measure knowledge graph factorization performance on the unified factorized latent space. Empirical results indicate the effectiveness of TriFac, surpassing previous state-of-the-art models on two MMEA datasets and a power system dataset.

Delta-band Activity Underlies Referential Meaning Representation during Pronoun Resolution.

Human language offers a variety of ways to create meaning, one of which is referring to entities, objects, or events in the world. One such meaning maker is understanding to whom or to what a pronoun in a discourse refers to. To understand a pronoun, the brain must access matching entities or concepts that have been encoded in memory from previous linguistic context. Models of language processing propose that internally stored linguistic concepts, accessed via exogenous cues such as phonological input of a word, are represented as (a)synchronous activities across a population of neurons active at specific frequency bands. Converging evidence suggests that delta band activity (1-3 Hz) is involved in temporal and representational integration during sentence processing. Moreover, recent advances in the neurobiology of memory suggest that recollection engages neural dynamics similar to those which occurred during memory encoding. Integrating from these two research lines, we here tested the hypothesis that neural dynamic patterns, especially in delta frequency range, underlying referential meaning representation, would be reinstated during pronoun resolution. By leveraging neural decoding techniques (i.e., representational similarity analysis) on a magnetoencephalogram data set acquired during a naturalistic story-listening task, we provide evidence that delta-band activity underlies referential meaning representation. Our findings suggest that, during spoken language comprehension, endogenous linguistic representations such as referential concepts may be proactively retrieved and represented via activation of their underlying dynamic neural patterns.

An effective knowledge graph entity alignment model based on multiple information

Entity alignment refers to matching entities with the same realistic meaning in different knowledge graphs. The structure of a knowledge graph provides the global signal for entity alignment. But in the real world, a knowledge graph provides insufficient structural information in general. Moreover, the problem of knowledge graph heterogeneity is common. The semantic and string information can alleviate the problems caused by the sparse and heterogeneous nature of knowledge graphs, yet both of them have not been fully utilized by most existing work. Therefore, we propose an entity alignment model based on multiple information (EAMI), which employs structural, semantic and string information. EAMI learns the structural representation of a knowledge graph by using multi-layer graph convolutional networks. To acquire more accurate entity vector representation, we incorporate the attribute semantic representation into the structural representation. In addition, to further improve entity alignment, we study the entity name string information. There is no training required to calculate the similarity of entity names. Our model is tested on publicly available cross-lingual datasets and cross-resource datasets, and the experimental results demonstrate the effectiveness of our model.

Leveraging Multi-Modal Information for Cross-Lingual Entity Matching across Knowledge Graphs

In recent years, the scale of knowledge graphs and the number of entities have grown rapidly. Entity matching across different knowledge graphs has become an urgent problem to be solved for knowledge fusion. With the importance of entity matching being increasingly evident, the use of representation learning technologies to find matched entities has attracted extensive attention due to the computability of vector representations. However, existing studies on representation learning technologies cannot make full use of knowledge graph relevant multi-modal information. In this paper, we propose a new cross-lingual entity matching method (called CLEM) with knowledge graph representation learning on rich multi-modal information. The core is the multi-view intact space learning method to integrate embeddings of multi-modal information for matching entities. Experimental results on cross-lingual datasets show the superiority and competitiveness of our proposed method.

A Multi-Scale Residential Areas Matching Method Considering Spatial Neighborhood Features

Residential areas is one of the basic geographical elements on the map and an important content of the map representation. Multi-scale residential areas matching refers to the process of identifying and associating entities with the same name in different data sources, which can be widely used in map compilation, data fusion, change detection and update. A matching method considering spatial neighborhood features is proposed to solve the complex matching problem of multi-scale residential areas. The method uses Delaunay triangulation to divide complex matching entities in different scales into closed domains through spatial neighborhood clusters, which can obtain many-to-many matching candidate feature sets. At the same time, the geometric features and topological features of the residential areas are fully considered, and the Relief-F algorithm is used to determine the weight values of different similarity features. Then the similarity and spatial neighborhood similarity of the polygon residential areas are calculated, after which the final matching results are obtained. The experimental results show that the accuracy rate, recall rate and F value of the matching method are all above 90%, which has a high matching accuracy. It can identify a variety of matching relationships and overcome the influence of certain positional deviations on matching results. The proposed method can not only take account of the spatial neighborhood characteristics of residential areas, but also identify complex matching relationships in multi-scale residential areas accurately with a good matching effect.

Coarse-to-Fine Entity Alignment for Chinese Heterogeneous Encyclopedia Knowledge Base

Entity alignment (EA) aims to automatically determine whether an entity pair in different knowledge bases or knowledge graphs refer to the same entity in reality. Inspired by human cognitive mechanisms, we propose a coarse-to-fine entity alignment model (called CFEA) consisting of three stages: coarse-grained, middle-grained, and fine-grained. In the coarse-grained stage, a pruning strategy based on the restriction of entity types is adopted to reduce the number of candidate matching entities. The goal of this stage is to filter out pairs of entities that are clearly not the same entity. In the middle-grained stage, we calculate the similarity of entity pairs through some key attribute values and matched attribute values, the goal of which is to identify the entity pairs that are obviously not the same entity or are obviously the same entity. After this step, the number of candidate entity pairs is further reduced. In the fine-grained stage, contextual information, such as abstract and description text, is considered, and topic modeling is carried out to achieve more accurate matching. The basic idea of this stage is to use more information to help judge entity pairs that are difficult to distinguish using basic information from the first two stages. The experimental results on real-world datasets verify the effectiveness of our model compared with baselines.

Network metrics for assessing the quality of entity resolution between multiple datasets1

Matching entities between datasets is a crucial step for combining multiple datasets on the semantic web. A rich literature exists on different approaches to this entity resolution problem. However, much less work has been done on how to assess the quality of such entity links once they have been generated. Evaluation methods for link quality are typically limited to either comparison with a ground truth dataset (which is often not available), manual work (which is cumbersome and prone to error), or crowd sourcing (which is not always feasible, especially if expert knowledge is required). Furthermore, the problem of link evaluation is greatly exacerbated for links between more than two datasets, because the number of possible links grows rapidly with the number of datasets. In this paper, we propose a method to estimate the quality of entity links between multiple datasets. We exploit the fact that the links between entities from multiple datasets form a network, and we show how simple metrics on this network can reliably predict their quality. We verify our results in a large experimental study using six datasets from the domain of science, technology and innovation studies, for which we created a gold standard. This gold standard, available online, is an additional contribution of this paper. In addition, we evaluate our metric on a recently published gold standard to confirm our findings.

A fully automated approach to a complete Semantic Table Interpretation

In recent years, there has been an increasing interest in extracting and annotating tables on the Web. This activity allows the transformation of text data into machine-readable formats to enable the execution of various artificial intelligence tasks, e.g. semantic search and dataset extension. Semantic Table Interpretation is the process of annotating elements in a table. Current approaches are mainly based on lexical matching algorithms that rely on metadata associated with tables or custom Knowledge Graphs. Their main limitations are due to the lack of metadata, the little use of contextual semantics, and the incompleteness of the proposed methods that do not include all the necessary steps. In this paper, we propose a comprehensive approach and a tool that provides an unsupervised method to annotate independent tables, possibly without header row or other external information. The approach is based on the definition of a context created from the elements within the table in order to discriminate among matching entities found in shared Knowledge Graphs and create high-quality annotations. The approach has achieved excellent results in an international challenge, thus proving its effectiveness.

Benchmarking Blocking Algorithms for Web Entities

An increasing number of entities are described by interlinked data rather than documents on the Web. Entity Resolution (ER) aims to identify descriptions of the same real-world entity within one or across knowledge bases in the Web of data. To reduce the required number of pairwise comparisons among descriptions, ER methods typically perform a pre-processing step, called \emph{blocking}, which places similar entity descriptions into blocks and thus only compare descriptions within the same block. We experimentally evaluate several blocking methods proposed for the Web of data using real datasets, whose characteristics significantly impact their effectiveness and efficiency. The proposed experimental evaluation framework allows us to better understand the characteristics of the missed matching entity descriptions and contrast them with ground truth obtained from different kinds of relatedness links.

Time and Space Efficient Large Scale Link Discovery using String Similarities

This paper proposes and evaluates time and space efficient methods for discovering links between matching entities in large data sets, using state of the art methods for measuring edit distance as a string similarity metric. The paper proposes and compares three filtering methods that build on a basic blocking technique to organize the target dataset, facilitating efficient pruning of dissimilar pairs. The proposed filtering methods are compared in terms of runtime and memory usage: The first method exploits the blocking structure using the triangle inequality in conjunction to the substring-matching criterion. The second method uses only the substring-matching criterion, while the third method uses the substring-matching criterion in conjunction to the frequency-matching criterion. Evaluation results show the pruning power of the different criteria used, also in comparison to the string matching functionality provided in LIMES and SILK, which are state-of-the-art tools for large-scale link discovery.

Towards task-based parallelization for entity resolution

Entity resolution (ER) refers to the problem of finding which virtual representations in one or more data sources refer to the same real-world entity. A central question in ER is how to find matching entity representations (so called duplicates) efficiently and in a scalable way. One general technique to address these issues is to leverage parallelization. In particular, almost all work on parallel ER focus on data parallelism. This paper focuses on task parallelism for ER. This type of parallelism allows to support incremental ER that offers incremental computation of the solution by streaming results of intermediate stages of ER as soon as they are computed. This possibly allows to obtain results in a more timely fashion and can also serve in a service-oriented setting with limited time or monetary budget. In summary, this paper presents a framework for task-parallelization of ER, supporting in particular ER of large amounts of semi-structured and heterogeneous data. We also discuss a possible implementation of our framework.

An automatic method for precise 3D registration of high resolution satellite images and Airborne LiDAR Data

ABSTRACTPrecise 3D registration of Light Detection and Ranging (LiDAR) data and High-Resolution Satellite Image (HRSI) is the prerequisite in the many remote sensing applications. An automatic registration process involves two main steps including the detection of corresponding entities and the estimation of a relating mathematical model. Typical matching techniques, which are generally developed to match consistent data sources, are prone to fail in case of matching between heterogeneous data sources (e.g. LiDAR and optical images). This paper proposes a three-step method to give in hand an accurate and automatic 3D registration technique between LiDAR data and the HRSI. The first step introduces a new product called Optical Consistent LiDAR Product (OCLP) which is meant to be consistent with HRSI from the radiometric point of view. The OCLP is generated using raster maps of the LiDAR heights and intensities along with information of the sun position at the acquisition time of HRSI. This new product proved to be very promising as a matching entity with HRSI. In the second step, a 3D model is estimated robustly through the matched points identified by the well-known Scale Invariant Feature Transform (SIFT) technique between the OCLP and the HRSI. The last step of the proposed method aims to strengthen this 3D model which is accomplished via iterative closest edge points matching technique. To do so, the coarse 3D model is iteratively improved based on the matching results obtained on the image edges. The proposed method was implemented on 20 different datasets containing various urban textures. The results indicate the effectiveness of the proposed method since in some cases it could achieve to sub-pixel accuracies which are the utmost expectation for a registration technique.

High-Accuracy Entity State Prediction Method Based on Deep Belief Network Toward IoT Search

The state of physical entity in the Internet of Things (IoT) has an obvious time-varying characteristic. Preliminarily selecting candidate entities by predicting their current state when searching match entities from massive ones can effectively reduce the communication overhead of IoT search system. The existing methods are all based on shallow learning theories whose performances are very limited. Thus, a high-accuracy entity state prediction method (HESPM) based on deep learning theory is proposed. The model of HESPM is built by utilizing the deep belief network. Then the contrastive divergence algorithm is adopted to train the model. Therefore, the dynamic evolution trend of entity state can be accurately perceived and the future entity state can be precisely predicted. Simulation results demonstrate the effectiveness of HESPM in enhancing the prediction accuracy and communication overhead performances.

Maverick

This paper presents Maverick, a system for discovering exceptional facts about entities in knowledge graphs. Maverick is built upon a beam-search based algorithmic framework which we proposed in a research paper that is published in SIGMOD 2018. In this demonstration proposal, we showcase an end-to-end system that includes a user-facing portal and a cache server. In Maverick, an exceptional fact about an entity of interest is modeled as a context-subspace pair, in which the subspace is a set of attributes and the context is defined by a graph query pattern of which the entity is a match, together with other matching entities. The entity is exceptional among the entities in the context, with regard to the sub-space. The portal allows users to search entities in a knowledge graph and explores exceptional facts about the entities of interest. It presents exceptional facts to users in forms of natural language sentences and illustration charts, for better interpretability of the discovered exceptional facts. The cache server stores intermediate computation results, such as pattern evaluations, exceptionality calculations, and candidate patterns. It is built for sharing computation across entities, such that repetitive computation across entities can be avoided.

Multiple data linkage using SSCCT for direct and semantic matching pair

Data Linking is a method of integrating multiple data items located on different sources and establishing links among entities of the same type or semantically relevant type. It is necessary to develop the data linkage techniques for different and semantically related items for interconnecting multiple data sources. In this paper, multiple data linkage is used to establish relation between matching entities of different types that are semantically related. The proposed method used Semantically Similar Class Clustering Tree (SSCCT) for implementing multiple data linkage. The SSCCT is built in such a way that it is easy to understand and can be transformed into association rules which are verified using WordNet ontology. The data source properties are represented as tree and the inner node, which consists of features from the first data set. The leaves of the tree represent features from the second data set that is matching with the first data set entities. The proposed method used semantic similarity estimation for pre-pruning process which is used to create Semantically Similar Class Clustering Tree effectively. Threshold value is used for decision making either the record pair is match or non-match.

Shadow-Based Hierarchical Matching for the Automatic Registration of Airborne LiDAR Data and Space Imagery

The automatic registration of LiDAR data and optical images, which are heterogeneous data sources, has been a major research challenge in recent years. In this paper, a novel hierarchical method is proposed in which the least amount of interaction of a skilled operator is required. Thereby, two shadow extraction schemes, one from LiDAR and the other from high-resolution satellite images, were used, and the obtained 2D shadow maps were then considered as prospective matching entities. Taken as the base, the reconstructed LiDAR shadows were transformed to image shadows using a four-step hierarchical method starting from a coarse 2D registration model and leading to a fine 3D registration model. In the first step, a general matching was performed in the frequency domain that yielded a rough 2D similarity model that related the LiDAR and image shadow masks. This model was further improved by modeling and compensating for the local geometric distortions that existed between the two heterogeneous data sources. In the third step, shadow masks, which were organized as segmented matched patches, were the subjects of a coinciding procedure that resulted in a coarse 3D registration model. In the last hierarchical step, that model was ultimately reinforced via a precise matching between the LiDAR and image edges. The evaluation results, which were conducted on six datasets and from different relative and absolute aspects, demonstrated the efficiency of the proposed method, which had a very promising accuracy on the order of one pixel.

Evaluating metaphor reification in tangible interfaces

Metaphors are a powerful conceptual device to reason about human actions. As such, they have been heavily used in designing and describing human computer interaction. Since they can address scripted text, verbal expression, imaging, sound, and gestures, they can also be considered in the design and analysis of multimodal interfaces. In this paper we discuss the description and evaluation of the relations between metaphors and their implementation in human computer interaction with a focus on tangible user interfaces (TUIs), a form of multimodal interface. The objective of this paper is to define how metaphors appear in a tangible context in order to support their evaluation. Relying on matching entities and operations between the domain of interaction and the domain of the digital application, we propose a conceptual framework based on three components: a structured representation of the mappings holding between the metaphor source, the metaphor target, the interface and the digital system; a conceptual model for describing metaphorical TUIs; three relevant properties, coherence, coverage and compliance, which define at what extent the implementation of a metaphorical tangible interface matches the metaphor. The conceptual framework is then validated and applied on a tangible prototype in an educational application.