Semantic Similarity Calculation Research Articles

Structural Process Pattern Matching Based on Graph Morphism Detection

Context: Processes are central to the operation of many systems or organizations. Process-centric systems, ranging from enterprise workflow systems to open distributed service compositions, have significantly increased in number and complexity. Objective: Designers of process-centric systems can benefit from process abstractions (including patterns) capturing and allowing the reuse of designs for frequent operational problems. Existing process patterns detection techniques have efficiency problems and difficulties to identify partial and inexact pattern instances. Method: We propose a process pattern detection technique based on a family of subgraph matching algorithms. The algorithms implement surjective graph morphism detection and a mechanism to incorporate semantic similarity computation for types and attributes of process graph elements. Results: Efficiency is addressed using simplified data structures, reducing the search space and its exploration. Match accuracy and time-complexity are demonstrated in an experimental study. Conclusions: Using process patterns allows business and technical processes to be provided as sharable service resources. Patterns can help to manage processes as configurable resources where a pattern can define a family of concrete customizable processes.

Semantic Mediation in MedPeer

Peer-to-Peer (P2P) infrastructure is an emerging paradigm that offers new opportunities for the development of large-scale distributed systems. This architecture combined with the new techniques introduced by semantic web as ontologies encouraged the emergence of new multi-source data integration possibilities for sharing information. A challenging problem in such systems is to find correspondences between concepts of their different ontologies. This is a necessary step before locating peers that are relevant with respect to a given query. In this paper, the authors propose a new ontology alignment method which deals with both linguistic and semantic characteristics of concepts and uses graph structure to explore multiple depth levels of neighborhood in calculation of semantic similarity which is the most important part of their global similarity measure. This function is implemented into their new P2P heterogeneous and distributed data integration system MedPeer.

A Novel Data Integration Framework Based on Unified Concept Model

Nowadays, data is being generated, collected, and analyzed at an unprecedented scale, data integration is the problem of combining data from heterogeneous, autonomous data sources, and providing users with a unified view of integrated data. To design a data integration framework, we need to address challenges, such as schema mapping, data cleaning, record linkage, and data fusion. In this paper, we briefly introduce the traditional data integration approaches, and then, a novel graph-based data integration framework based on unified concept model (UCM) is proposed to address real-world refueling data integration problems. Within this framework, schema mapping was carried out and metadata from heterogeneous sources is integrated in a UCM. UCM has the benefits of being easy to update. It is also important for effective schema mapping and data transformation. By following the structure of UCM, data from different sources is automatically transformed into instance data and linked together by using semantic similarity computation metrics, finally the data is stored in graph database. Experiments are carried out based on heterogeneous data from refueling records, social networks of astroturfers, and vehicle trajectories. Experimental results and reference implementation demonstrations show good precision and recall of the proposed framework.

A Novel Group Wise-Based Method for Calculating Human miRNA Functional Similarity

The measurement of human miRNA functional similarity is an important research for studying miRNA-related therapeutic strategy. Pair wise-based approaches using disease-miRNA associations have recently become a popular tool for inferring miRNA functional similarity. However, the miRNA functional similarity is vitally influenced by calculation of the disease semantic similarity in those methods. Moreover, integrating information content with hierarchical structure can improve calculation of the miRNA functional similarity. Therefore, we propose a group-wise method for inferring the miRNA functional similarity, named GMFS. First, the information content is computed by using disease MeSH descriptors to describe the specific of disease. Second, the acquirement of disease feature is based on the hierarchical structure as well as the information content of disease. Finally, the miRNA functional similarity is measured by using both miRNA-disease associations and the disease feature. To validate the effectiveness of the GMFS, we compare our method with several existing methods in terms of the average similarity of intra-family, inter-family, intra-cluster, and inter-cluster groups. The $p$ -values achieved by non-parametric test further indicate that the GMFS could have reliable miRNA similarity. Besides, the correlation between other biological information of the miRNA and the miRNA functional similarity is analyzed. The influence of the varying parameter is shown. We also demonstrate that the constructed network based on the miRNA functional similarity is a scale-free and small-world network. The superior performance on uncovering lymphoma-related miRNAs explains the ability of the GMFS inferring the miRNA functional similarity.

OntologyX: a suite of R packages for working with ontological data

SummaryOntologies are widely used constructs for encoding and analyzing biomedical data, but the absence of simple and consistent tools has made exploratory and systematic analysis of such data unnecessarily difficult. Here we present three packages which aim to simplify such procedures. The ontologyIndex package enables arbitrary ontologies to be read into R, supports representation of ontological objects by native R types, and provides a parsimonius set of performant functions for querying ontologies. ontologySimilarity and ontologyPlot extend ontologyIndex with functionality for straightforward visualization and semantic similarity calculations, including statistical routines.Availability and Implementation ontologyIndex, ontologyPlot and ontologySimilarity are all available on the Comprehensive R Archive Network website under https://cran.r-project.org/web/packages/.Supplementary information Supplementary data are available at Bioinformatics online.

Cloud based automated framework for semantic rich ontology construction and similarity computation for E-health applications

Abstract Ontology structure, a core of semantic web is an excellent tool for knowledge representation and semantic visualization. Moreover, knowledge reuse is made possible through similarity measure estimation between two ontologies, threshold estimation and use of simple if-then rules for checking relevancy and irrelevancy measures. Reduced semantic representations of the ontology provide reduced knowledge visualization which is critical especially for e-health data processing and analysis. This usually occurs due to the presence of implicit knowledge and polymorphic objects and can be made semantically rich through the construction by resolving this implicit knowledge occurring in the form of non-dominant words and conditional dependence actions. This paper presents the working of the automated framework for the construction of semantic rich ontology structures and store in the repository. This construction uses dyadic deontic logic based Graph Derivation Representation in order to construct semantically rich ontologies. Moreover, in order to retrieve a set of relevant documents in response to the cloud user document, the degree of similarity between two ontologies is estimated using the traditional cosine similarity measure and simple if-then rules are used to determine the number of relevant documents and obtain such document's metadata for further processing. These working modules will be extremely beneficial to the authenticated cloud users for document retrieval, information extraction and domain dictionary construction which are especially used for e-health applications. The proposed framework is implemented using diabetes dataset and the effectiveness of the experimental results is high when compared to other Graph Derivation Representation methods. The graphical results shown in the paper is an added visualization for viewing the performance of the proposed framework.

Matching Mechanism of Web Service Based on Hybrid Semantic Similarity Computation

Fuzzy search algorithm with hybrid semantic similarity is proposed aiming at serious performance issues in information retrieval, which results from fuzzy search condition, in search engine land. First of all, new conceptual extraction method is proposed according to similarity calculation concept; after that, TF-IQF is adopted to divide the link into tabs, and the set comprised of these tabs is used for indicating the query; ultimately, binary graph is constructed to identify related queries and is employed to compute query similarity. Experimental results show that proposed algorithm has achieved better recall ratio, retrieval precision and F-measure compared with clicking document, related queries and reverse query algorithm.

Semantic similarity algorithm based on agricultural ontology and its application on crop ontology.

Ontology represents a structured view of the domain containing rich semantic meanings, thus plays an important role for various knowledge-intensive applications. Domain ontology contains the concept of complete information and extensive links between concepts. Construction of agricultural domain ontology can provide the foundation of knowledge organization for vertical agricultural research engine and promoting agricultural informationization and realizing cooperative service of agricultural information. Semantic similarity measure plays an important role in information retrieval and information integration based on ontology. While, traditional semantic similarity algorithms of domain ontology only focus on single influencing factor, which leads to poor convergence performances, lower accuracy, strong subjectivity and other defects. In this paper, a weighted semantic similarity algorithm based on agricultural domain ontology was proposed. According to the characteristics of the different structure of ontology, the major factors that influence the similarity are the structure factor, property of the concept, information, etc. But the structural factors are impacted by relationship type, density of node, depth of node and other factors. First, according to the structural characteristics of ontology model, a new method for calculating the node density was proposed in this study. At the same time, an integrated structure similarity model based on relationship type, node density, depth integrated structure similarity, semantic distance was given, which was called the structure factors. Second, according to the literature and empirical knowledge, the property grid of ontology concept pairs was accessed to gain the attributes of the concept. Third, according to ontology hierarchial network, B-U probability based on root and leaf nodes and semantic information was calculated, which did not rely on the expertise and was objective. Fourth, combining semantic structure, information and property factors, an integrated semantic similarity algorithm was proposed, which considered that different impact factors had a different important degree in the calculation of semantic similarity and were given different weights to agricultural ontology relations. Finally, taking semantic similarity computation of part of agriculture ontology for example, the calculation process of semantic similarity on sweet corn and waxy maize was enumerated in detail. According to the semantic similarity algorithm proposed in this paper, comparing the calculation results of semantic similarity (0.8206) and standard deviation (0.0565) with other algorithms, it was closer to the intuitive cognition and expert advice, which can effectively improve the accuracy and validity of semantic similarity computation. In this paper, we presented the effort of computing the semantic similarity values via studying the relationship between concept pairs of agricultural ontologies at different depth of ontology hierarchical structure. We evaluated the accuracy of semantic similarity calculation between four different algorithms (algorithm in this paper, algorithm based on information content, algorithm based on distance, and algorithm using standard deviation commonly applied in statistics). The results of this study demonstrated that with proper selection of parameters and comprehensive similarity computation measures, we can significantly reduce difficulty of distinguishing the concept of weak correlation. This study provides a deeper understanding of the application of semantic similarity to agricultural ontologies, and shows how to choose appropriate semantic similarity measures for agricultural information retrieval. © 2016, Editorial Department of the Transactions of the Chinese Society of Agricultural Engineering. All right reserved.

SSC Based RS: An Efficient Service Recommendation System for Handling Big Data Applications

Objectives: To find an appropriate web service and reduce the time taken for introducing web service, to improve parallel processing, to reduce the complexity and to improve its scalability and efficiency in big data environment. Methods: MapReduce framework in Hadoop platform is for increase the efficiency and scalability in big data domain, SSC based RS, web service information are structured in hierarchical format. The proposed system calculates the semantic comparison between the big data applications. Findings: SSC based RS (Semantic Similarity Calculation Based Recommendation System) is used to efficiently suggest better services for the requested users, by using semantic dictionary the semantic similarity will be calculated. Here, the services are stored in the hierarchical structure will increase the recommendation process faster. An experimental result shows that our proposed algorithm provides a suitable recommended service compared to other existing approaches. Applications/Improvement: In Big Data the proposed technique improves the efficiency and scalability by applying MapReduce parallel processing standard on Hadoop environment.

An approach to semantic query expansion system based on Hepatitis ontology.

BackgroundOntology development, as an increasingly practical vehicle applied in various fields, plays a significant role in knowledge management. This paper, focusing on constructing and querying a hepatitis ontology, aims to provide a framework for ontology-based medical services. The paper is devoted to the algorithm of query expansion for the hepatitis ontology, including synonym expansion, hypernym/hyponym expansion and expansion of similar words. It applies semantic similarity calculation to judge the similarity of retrieval terms.ResultsThe paper proposes a new prototype system. The accuracy of query expansion is improved in both precision@40 and AP@40, which indicates that query expansion improves the accuracy of the query after using the method proposed in this paper.ConclusionsThe paper has adopted semantic similarity computing to improve retrieval performance. Experiments show that search precision of query expansion is higher based on domain concept relationship.

An Intelligent Web Search Using Multi-Document Summarization

Information available on the internet is huge, diverse and dynamic. Current Search Engine is doing the task of intelligent help to the users of the internet. For a query, it provides a listing of best matching or relevant web pages. However, information for the query is often spread across multiple pages which are returned by the search engine. This degrades the quality of search results. So, the search engines are drowning in information, but starving for knowledge. Here, we present a query focused extractive summarization of search engine results. We propose a two level summarization process: identification of relevant theme clusters, and selection of top ranking sentences to form summarized result for user query. A new approach to semantic similarity computation using semantic roles and semantic meaning is proposed. Document clustering is effectively achieved by application of MDL principle and sentence clustering and ranking is done by using SNMF. Experiments conducted demonstrate the effectiveness of system in semantic text understanding, document clustering and summarization.

Issue Tracking System based on Ontology and Semantic Similarity Computation

A computer program is never truly finished; changes are a constant feature of computer program development, there are always something need to be added, redone, or fixed. Therefore, issue-tracking systems are widely used on the system development to keep track of reported issues. This paper proposes a new architecture for automated issue tracking system based on ontology and semantic similarity measure. The proposed architecture integrates several natural languages techniques including vector space model, domain ontology, term-weighting, cosine similarity measure, and synonyms for semantic expansion. The proposed system searches for similar issue templates, which are characteristic of certain fields, and identifies similar issues in an automated way, possible experts and responses are extracted finally. The experimental results demonstrated the accuracy of the new architecture, the experiment result indicates that the accuracy reaches to 94%.

The Research of Chinese Words Semantic Similarity Calculation with Multi-Information

Text similarity has a relatively wide range of applications in many fields, such as intelligent information retrieval, question answering system, text rechecking, machine translation, and so on. The text similarity computing based on the meaning has been used more widely in the similarity computing of the words and phrase. Using the knowledge structure of the and its method of knowledge description, taking into account the other factor and weight that influenced similarity, making full use of depth and density of the Concept-Sememe tree, an improved method of Chinese word similarity calculation based on semantic distance was provided in this paper. Finally the effectiveness of this method was verified by the simulation results.

An Optimization for Hybrid Semantic Similarity Computation

Semantic similarity computation is of great importance in many applications such as natural language processing, knowledge acquisition and information retrieval. In recent years, many concept similarity measures have been developed for ontology and lexical taxonomy. Generally speaking, ontology concepts semantic similarity computation is tedious and time-consuming. This paper puts forward an optimization algorithm to simplify semantic similarity computation. The optimization algorithm utilizes hierarchical relationship between concepts to simplify similarity computation process. Simulation experiments showed the optimization algorithm could make similarity computation simple and convenient, and similarity computation speed was improved by one time. The more complexity an ontology structure, and the bigger the maximum depth of ontology, the more significantly the performance improved.

Summarizing large text collection using topic modeling and clustering based on MapReduce framework

Document summarization provides an instrument for faster understanding the collection of text documents and has a number of real life applications. Semantic similarity and clustering can be utilized efficiently for generating effective summary of large text collections. Summarizing large volume of text is a challenging and time consuming problem particularly while considering the semantic similarity computation in summarization process. Summarization of text collection involves intensive text processing and computations to generate the summary. MapReduce is proven state of art technology for handling Big Data. In this paper, a novel framework based on MapReduce technology is proposed for summarizing large text collection. The proposed technique is designed using semantic similarity based clustering and topic modeling using Latent Dirichlet Allocation (LDA) for summarizing the large text collection over MapReduce framework. The summarization task is performed in four stages and provides a modular implementation of multiple documents summarization. The presented technique is evaluated in terms of scalability and various text summarization parameters namely, compression ratio, retention ratio, ROUGE and Pyramid score are also measured. The advantages of MapReduce framework are clearly visible from the experiments and it is also demonstrated that MapReduce provides a faster implementation of summarizing large text collections and is a powerful tool in Big Text Data analysis.

A New Measure of the Calculation of Semantic Distance between Ontology Concepts

Semantic similarity calculation models are found in many applications, with the aim to give additional knowledge to reason about their data. The choice of a similarity measure is quite crucial for a successful implementation of reasoning. In this work, we present an update of similarity calculation presented by Wu and Palmer which is considered the fastest in time generation of similarity. The results obtained show that the measure produced provides a significant improvement in the relevance of the values produced for the similarity of two concepts in ontology.

Semantic Similarity Computation Based on Multi-Features Fusion

Semantic similarity is a core technique of many NLP research fields. However, stateof-the-art metrics for semantic similarity computation often operate at different levels, e.g., words or sentences. In this paper, semantic similarity computation metrics are firstly introduced and the quality is measured in order to determine their advantages and limitations; then a new semantic similarity metric based on multi-features fusion is proposed. Distributed representations of words are used for alignment-based disambiguation operation, and Wikipedia tags are used to enhance the performance of our approach. The proposed metric is unsupervised, and can be applied at different levels e.g., single words or entire documents. The metric is evaluated on both English and Chinese datasets, it is shown that the precision and recall scores are higher than metrics which simply using knowledge base or distributed representation of words.

Human-inspired semantic similarity between sentences

Abstract Following the Principle of Compositionality, the meaning of a complex expression is influenced, to some extent, not only by the meanings of its individual words, but also the structural way the words are assembled. Compositionality has been a central research issue for linguists and psycholinguists. However, it remains unclear how does syntax influence the meaning of a sentence. In this paper, we propose an interdisciplinary approach to better understand that relation. We present an empirical study that seeks for the different weights given by humans to different syntactic roles when computing semantic similarity. In order to test the validity of the hypotheses derived from the psychological study, we use a computational paradigm. We incorporate the results of that study to a psychologically plausible computational measure of semantic similarity. The results shown by this measure in terms of correlation with human judgments on a paraphrase recognition task confirm the different importance that humans give to different syntactic roles in the computation of semantic similarity. This results contrast with generative grammar theories but support neurolinguistic evidence.

An Ontology-Based Semantic Similarity Measure Considering Multi-Inheritance in Biomedicine

Computation of semantic similarity between words for text understanding is a vital issue in many applications such as word sense disambiguation, document categorization, and information retrieval. In recent years, different paradigms have been proposed to compute semantic similarity based on different ontologies and knowledge resources. In this paper, we propose a new similarity measure combining both superconcepts of the evaluated concepts and their common specificity feature. The common specificity feature considers the depth of the Least Common Subsumer (LCS) of two concepts and the depth of the ontology to obtain more semantic evidence. The multiple inheritance phenomenon in a large and complex taxonomy is taken into account by all superconcepts of the evaluated concepts. We evaluate and compare the correlation obtained by our measure with human scores against other existing measures exploiting SNOMED CT as the input ontology. The experimental evaluations show the applicability of the measure on different datasets and confirm the efficiency and simplicity of our proposed measure.

DOSE: an R/Bioconductor package for disease ontology semantic and enrichment analysis.

Disease ontology (DO) annotates human genes in the context of disease. DO is important annotation in translating molecular findings from high-throughput data to clinical relevance. DOSE is an R package providing semantic similarity computations among DO terms and genes which allows biologists to explore the similarities of diseases and of gene functions in disease perspective. Enrichment analyses including hypergeometric model and gene set enrichment analysis are also implemented to support discovering disease associations of high-throughput biological data. This allows biologists to verify disease relevance in a biological experiment and identify unexpected disease associations. Comparison among gene clusters is also supported. DOSE is released under Artistic-2.0 License. The source code and documents are freely available through Bioconductor (http://www.bioconductor.org/packages/release/bioc/html/DOSE.html). Supplementary data are available at Bioinformatics online. gcyu@connect.hku.hk or tqyhe@jnu.edu.cn.