Wikipedia Concepts Research Articles

Beyond Literal Meaning: Uncover and Explain Implicit Knowledge in Code Through Wikipedia-Based Concept Linking

When reusing or modifying code, developers need to understand the implicit knowledge behind a piece of code in addition to the literal meaning of code. Such implicit knowledge involves related concepts and their explanations. Uncovering and understanding the implicit knowledge in code are challenging due to the extensive use of abbreviations, scattered expressions of concepts, and ambiguity of concept mentions. In this paper, we propose an automatic approach (called CoLiCo) that can uncover implicit concepts in code and link the uncovered concepts to Wikipedia. Based on a trained identifier embedding model, CoLiCo identifies Wikipedia concepts mentioned in a given code snippet and excerpts a paragraph-level explanation from Wikipedia for each concept. During the process, CoLiCo resolves identifier abbreviation (i.e., concepts mentioned in the form of abbreviations) and identifier aggregation (i.e., concepts mentioned by an aggregation of multiple identifiers) based on identifier embedding and mining of identifier abbreviation/aggregation relations. Experimental study shows that CoLiCo outperforms a general entity linking approach by 38.7% in the correctness of concept linking and identifies 96.7% more correct concept linkings on a dataset with 629 code snippets. The concept linking is significant for program understanding in 54% code snippets. Our user study shows that CoLiCo can significantly shorten the time and improve the correctness in code comprehension tasks that intensively involve implicit knowledge.

Exploiting Wikipedia to Measure the Semantic Relatedness between Arabic Terms

Measuring the semantic relatedness between words or terms plays an important role in many domains such as linguistics and artificial intelligence. Although this topic has been widely explored in the literature, most efforts focused on the English text, while little has been done to measure the similarity between Arabic terms. A growing number of semantic relatedness measures have relied on an underlying background knowledge such as Wikipedia. They often map terms to Wikipedia concepts, and then use the content or hyperlink structure of the corresponding Wikipedia articles to estimate the similarity between terms. However, existing approaches mostly focused on the English version of Wikipedia, while limited work has been done on the Arabic version. This work proposes an approach that takes advantage of Wikipedia features to measure the relationship between Arabic terms. It exploits two types of relations to gain rich features for the similarity measure, which are: the context-based relation and the category-based relation. The context-based relation is measured based on the intersection between incoming links of Wikipedia articles, while the category-based relation is measured by utilizing the taxonomy of Wikipedia categories. The proposed approach was evaluated based on a translated version of the WordSimilarity-353 benchmark dataset. The results show that our approach generally outperforms several approaches in the literature that use the same dataset in English. However, the poor structure and content of the Arabic version of Wikipedia compared to the English version has resulted in several incorrect similarity scores.

A BERT-Based Approach for Extracting Prerequisite Relations among Wikipedia Concepts

Concept prerequisite relation prediction is a common task in the field of knowledge discovery. Concept prerequisite relations can be used to rank learning resources and help learners plan their learning paths. As the largest Internet encyclopedia, Wikipedia is composed of many articles edited in multiple languages. Basic knowledge concepts in a variety of subjects can be found on Wikipedia. Although there are many knowledge concepts in each field, the prerequisite relations between them are not clear. When we browse pages in an area on Wikipedia, we do not know which page to start. In this paper, we propose a BERT-based Wikipedia concept prerequisite relation prediction model. First, we created two types of concept pair features, one is based on BERT sentence embedding and the other is based on the attributes of Wikipedia articles. Then, we use these two types of concept pair features to predict the prerequisite relations between two concepts. Experimental results show that our proposed method performs better than state-of-the-art methods for English and Chinese datasets.

Understanding Cybersecurity Threat Trends Through Dynamic Topic Modeling.

Cybersecurity threats continue to increase and are impacting almost all aspects of modern life. Being aware of how vulnerabilities and their exploits are changing gives helpful insights into combating new threats. Applying dynamic topic modeling to a time-stamped cybersecurity document collection shows how the significance and details of concepts found in them are evolving. We correlate two different temporal corpora, one with reports about specific exploits and the other with research-oriented papers on cybersecurity vulnerabilities and threats. We represent the documents, concepts, and dynamic topic modeling data in a semantic knowledge graph to support integration, inference, and discovery. A critical insight into discovering knowledge through topic modeling is seeding the knowledge graph with domain concepts to guide the modeling process. We use Wikipedia concepts to provide a basis for performing concept phrase extraction and show how using those phrases improves the quality of the topic models. Researchers can query the resulting knowledge graph to reveal important relations and trends. This work is novel because it uses topics as a bridge to relate documents across corpora over time.

Tracking Knowledge Propagation Across Wikipedia Languages

In this paper, we present a dataset of inter-language knowledge propagation in Wikipedia. Covering the entire 309 language editions and 33M articles, the dataset aims to track the full propagation history of Wikipedia concepts, and allow follow-up research on building predictive models of them. For this purpose, we align all the Wikipedia articles in a language-agnostic manner according to the concept they cover, which results in 13M propagation instances. To the best of our knowledge, this dataset is the first to explore the full inter-language propagation at a large scale. Together with the dataset, a holistic overview of the propagation and key insights about the underlying structural factors are provided to aid future research. For example, we find that although long cascades are unusual, the propagation tends to continue further once it reaches more than four language editions. We also find that the size of language editions is associated with the speed of propagation. We believe the dataset not only contributes to the prior literature on Wikipedia growth but also enables new use cases such as edit recommendation for addressing knowledge gaps, detection of disinformation, and cultural relationship analysis.

A semi-explicit short text retrieval method combining Wikipedia features

With the advantages such as openness, interactivity, immediacy, and simplicity, the large number of short text data appear in the Web information space. Considering the short length, little information, sparse features and irregular grammar, the traditional information analyzing and retrieval technologies cannot deal with short text effectively. In view of the above problems, in this paper a new short text retrieval method based on the current mainstream semantic knowledge source, Wikipedia, is proposed. To be specific, a semantic feature selection algorithm is proposed to return the top k most relevant Wikipedia concepts as the whole vector space for a given short text. Thus, by analyzing the topic information of the semantic features contained in Wikipedia concepts, we propose some formulas to determine the association coefficient list between different components of the corresponding positions in two different feature vectors. On this basis, a new semantic relatedness assessment method under this lower dimensional semantic space is designed. According to computing and sorting the semantic relatedness between user queries and the target short text, a novel semi-explicit short text retrieval method combining Wikipedia concept feature and the corresponding topic information is proposed. Lastly, based on the experimental results on twitter subsets, we verify that our proposal has advantages over other some current retrieval methods on MAP, P@k and R-Prec, and can return more valid results.

An approach for measuring semantic similarity between Wikipedia concepts using multiple inheritances

Wikipedia provides a huge collaboratively made semi-structured taxonomy called Wikipedia category graph (WCG), which can be utilized as a Knowledge Graph (KG) to measure the semantic similarity (SS) between Wikipedia concepts. Previously, several Most Informative Common Ancestor-based (MICA-based) SS methods have been proposed by intrinsically manipulating the taxonomic structure of WCG. However, some basic structural issues in WCG such as huge size, branching factor and multiple inheritance relations hamper the applicability of traditional MICA-based and multiple inheritance-based approaches in it. Therefore, in this paper, we propose a solution to handle these structural issues and present a new multiple inheritance-based SS approach, called Neighborhood Ancestor Semantic Contribution (NASC). In this approach, firstly, we define the neighborhood of a category (a taxonomic concept in WCG) to define its semantic space. Secondly, we describe the semantic value of a category by aggregating the intrinsic IC-based semantic contribution weights of its semantically relevant multiple ancestors. Thirdly, based on our approach, we propose six different methods to compute the SS between Wikipedia concepts. Finally, we evaluate our methods on gold standard word similarity benchmarks for English, German, Spanish and French languages. The experimental evaluation demonstrates that the proposed NASC-based methods remarkably outperform traditional MICA-based and multiple inheritance-based approaches.

Assessing semantic similarity between concepts: A weighted‐feature‐based approach

SummaryTraditional feature‐based semantic similarity (SS) approaches exploit the Wikipedia features in term of sets. They evaluate the similarity of concepts based on the commonalities among their feature sets. However, these feature‐based approaches treat all the features equally in similarity evaluation. Therefore, they ignore the underlying statistics of the features and consequently lose the essential semantic details about them. One solution is that each feature can be assigned a specific weight using its statistics. This weight will reflect the relative importance of a feature in similarity evaluation. Therefore, in this paper, based on two statistical models, ie, information content and TFIDF, we propose some hybrid semantic similarity measurement methods. Firstly, we propose some new methods called weighting functions to compute the weights of the features and feature sets in Wikipedia. Secondly, based on the weighting functions, we propose some new weighted feature‐based SS approaches for Wikipedia concepts. Thirdly, we evaluate the proposed methods on well‐known benchmarks for English, German, French, and Spanish languages. Finally, we compare the performance of our methods with the traditional feature‐based and some state‐of‐the‐art SS approaches. The experimental evaluation shows that our weighted methods perform better than the traditional feature‐based and some state‐of‐the‐art approaches in similarity evaluation.

An efficient approach for measuring semantic relatedness using Wikipedia bidirectional links

The measurement of the semantic relatedness between concepts is an important fundamental research topic in natural language processing. The link-based model is the most promising relatedness method in Wikipedia-based measures because its manually defined links in Wikipedia are refined and close to the semantics of humans. This paper proposes a Wikipedia two-way link model to extend the existing Wikipedia one-way out-link model, which has a low dimension and a high efficiency, as well as being easy to implement and repeat. First, this model utilizes the out-links and in-links of concepts in Wikipedia to combine into a bidirectional link vector for concept semantic interpreter and uses a TF*IDF-based bidirectional weight method to uniformly calculate the strength of the mutual association between a given concept and its out-link or in-link concept. Second, we propose a disambiguation strategy based on the social awareness of senses that directly sorts the out-links within a disambiguation page in the order in which they occur in the disambiguation page and adopts an adjustable threshold to determine how many senses will be selected. Moreover, we also propose new vector similarity metrics based on logarithm and exponent to improve the comprehensive performance of the semantic relatedness measurements based on Wikipedia links. The experimental results on some well-recognized datasets demonstrate that our model surpasses the existing popular Naive Explicit Semantic Analysis (Naive-ESA) and Wikipedia Out-Link vector-based Measure (WOLM) methods in the current Wikipedia versions and that our bidirectional link model significantly improves the performance of the existing one-way link model in practical applications.

SRL-ESA-TextSum: A text summarization approach based on semantic role labeling and explicit semantic analysis

Automatic text summarization attempts to provide an effective solution to today’s unprecedented growth of textual data. This paper proposes an innovative graph-based text summarization framework for generic single and multi document summarization. The summarizer benefits from two well-established text semantic representation techniques; Semantic Role Labelling (SRL) and Explicit Semantic Analysis (ESA) as well as the constantly evolving collective human knowledge in Wikipedia. The SRL is used to achieve sentence semantic parsing whose word tokens are represented as a vector of weighted Wikipedia concepts using ESA method. The essence of the developed framework is to construct a unique concept graph representation underpinned by semantic role-based multi-node (under sentence level) vertices for summarization. We have empirically evaluated the summarization system using the standard publicly available dataset from Document Understanding Conference 2002 (DUC 2002). Experimental results indicate that the proposed summarizer outperforms all state-of-the-art related comparators in the single document summarization based on the ROUGE-1 and ROUGE-2 measures, while also ranking second in the ROUGE-1 and ROUGE-SU4 scores for the multi-document summarization. On the other hand, the testing also demonstrates the scalability of the system, i.e., varying the evaluation data size is shown to have little impact on the summarizer performance, particularly for the single document summarization task. In a nutshell, the findings demonstrate the power of the role-based and vectorial semantic representation when combined with the crowd-sourced knowledge base in Wikipedia.

A Sample Extension Method Based on Wikipedia and Its Application in Text Classification

Text classification is a topic in natural language processing that is particularly useful for Internet information processing. Methods based on supervised learning require a large amount of manually annotated training samples. The annotation of training samples is time consuming, and performance relies heavily on the quality of the training samples. This paper presents a text classification method based on sample extension. The extension is based on the correlation of the labeled sample data and the concepts in Wikipedia. Combined with the rich link relationships between concepts, we selected appropriate articles from Wikipedia to expand the training sample set. By introducing the large amount of rich semantic concept pages that are contained in Wikipedia along with links that are related to different pages, our approach enhances the performance and generalization of the classifier. Experiments demonstrate that the performance of the method proposed in this paper is better than that of both supervised and semi-supervised methods.

Improving the visibility of library resources via mapping library subject headings to Wikipedia articles

PurposeLinking libraries and Wikipedia can significantly improve the quality of services provided by these two major silos of knowledge. Such linkage would enrich the quality of Wikipedia articles and at the same time increase the visibility of library resources. To this end, the purpose of this paper is to describe the design and development of a software system for automatic mapping of FAST subject headings, used to index library materials, to their corresponding articles in Wikipedia.Design/methodology/approachThe proposed system works by first detecting all the candidate Wikipedia concepts (articles) occurring in the titles of the books and other library materials which are indexed with a given FAST subject heading. This is then followed by training and deploying a machine learning (ML) algorithm designed to automatically identify those concepts that correspond to the FAST heading. In specific, the ML algorithm used is a binary classifier which classifies the candidate concepts into either “corresponding” or “non-corresponding” categories. The classifier is trained to learn the characteristics of those candidates which have the highest probability of belonging to the “corresponding” category based on a set of 14 positional, statistical, and semantic features.FindingsThe authors have assessed the performance of the developed system using standard information retrieval measures of precision, recall, and F-score on a data set containing 170 FAST subject headings manually mapped to their corresponding Wikipedia articles. The evaluation results show that the developed system is capable of achieving F-scores as high as 0.65 and 0.99 in the corresponding and non-corresponding categories, respectively.Research limitations/implicationsThe size of the data set used to evaluate the performance of the system is rather small. However, the authors believe that the developed data set is large enough to demonstrate the feasibility and scalability of the proposed approach.Practical implicationsThe sheer size of English Wikipedia makes the manual mapping of Wikipedia articles to library subject headings a very labor-intensive and time-consuming task. Therefore, the aim is to reduce the cost of such mapping and integration.Social implicationsThe proposed mapping paves the way for connecting libraries and Wikipedia as two major silos of knowledge, and enables the bi-directional movement of users between the two.Originality/valueTo the best of the authors’ knowledge, the current work is the first attempt at automatic mapping of Wikipedia to a library-controlled vocabulary.

A graph-based semantic relatedness assessment method combining wikipedia features

Semantic relatedness assessment between concepts is a critical issue in many domains such as artificial intelligence, information retrieval, psychology, biology, linguistics and cognitive science. Therefore, several methods assess relatedness by exploiting knowledge bases to express the semantics of concepts. However, there are some limitations such as high-dimensional space, high-computational complexity, fitting non-dynamic domains. Considering that Wikipedia, a domain-independent encyclopedic repository, which provides very large coverage, has been exploited by many methods as a huge semantic resource. In this paper, we propose a novel graph-based relatedness assessment method using Wikipedia features to avoid some of the limitations and drawbacks mentioned above. Firstly, for each term in a word pair, the top k most relevant Wikipedia concepts are returned by the Naive-ESA algorithm to reduce the dimensional space of Explicit Semantic Analysis (ESA) method. Secondly, for each different candidate concept in two relevant concept sets, we collect its categories set from the Wikipedia Category Graph (WCG). Based on the categories in WCG network, the relatedness between concepts at the correspondence position of the two sorted concept sets is computed as the association coefficient. Thirdly, based on this parameter, a novel relatedness assessment metric is presented. The evaluation is performed on some datasets well-recognized as benchmarks, using several widely used metrics and a new metric designed by ourselves. The result demonstrates that our method has a better correlation with the intuitions of human judgments than other related works.

Semantic concept model using Wikipedia semantic features

Wikipedia has become a high coverage knowledge source which has been used in many research areas such as natural language processing, text mining and information retrieval. Several methods have been introduced for extracting explicit or implicit relations from Wikipedia to represent semantics of concepts/words. However, the main challenge in semantic representation is how to incorporate different types of semantic relations to capture more semantic evidences of the associations of concepts. In this article, we propose a semantic concept model that incorporates different types of semantic features extracting from Wikipedia. For each concept that corresponds to an article, four semantic features are introduced: template links, categories, salient concepts and topics. The proposed model is based on the probability distributions that are defined for these semantic features of a Wikipedia concept. The template links and categories are the document-level features which are directly extracted from the structured information included in the article. On the other hand, the salient concepts and topics are corpus-level features which are extracted to capture implicit relations among concepts. For the salient concepts feature, the distributional-based method is utilised on the hypertext corpus to extract this feature for each Wikipedia concept. Then, the probability product kernel is used to improve the weight of each concept in this feature. For the topic feature, the Labelled latent Dirichlet allocation is adapted on the supervised multi-label of Wikipedia to train the probabilistic model of this feature. Finally, we used the linear interpolation for incorporating these semantic features into the probabilistic model to estimate the semantic relation probability of the specific concept over Wikipedia articles. The proposed model is evaluated on 12 benchmark datasets in three natural language processing tasks: measuring the semantic relatedness of concepts/words in general and in the biomedical domain, semantic textual relatedness measurement and measuring the semantic compositionality of noun compounds. The model is also compared with five methods that depends on separate semantic features in Wikipedia. Experimental results show that the proposed model achieves promising results in three tasks and outperforms the baseline methods in most of the evaluation datasets. This implies that incorporation of explicit and implicit semantic features is useful for representing semantics of concepts in Wikipedia.

Discovering taxonomies in Wikipedia by means of grammatical evolution

This work applies grammatical evolution to identify taxonomic hierarchies of concepts from Wikipedia. Each article in Wikipedia covers a topic and is cross-linked by hyperlinks that connect related topics. Hierarchical taxonomies and their generalization to ontologies are a highly useful resource for many applications since they enable semantic search and reasoning. Thus, the automatic identification of taxonomies composed of concepts associated with linked Wikipedia pages has attracted much attention. We have developed a system which arranges a set of Wikipedia concepts into a taxonomy. This technique is based on the relationships among a set of features extracted from the contents of the Wikipedia pages. We have used a grammatical evolution algorithm to discover the best way of combining the considered features in an explicit function. Candidate functions are evaluated by applying a genetic algorithm to approximate the optimal taxonomy that the function can provide for a number of training cases. The fitness is computed as an average of the precision obtained by comparing, for the set of training cases, the taxonomy provided by the evaluated function with the reference one. Experimental results show that the proposal is able to provide valuable functions to find high-quality taxonomies.

Incorporating Wikipedia concepts and categories as prior knowledge into topic models

Incorporating Wikipedia concepts and categories as prior knowledge into topic models

DBpedia based Ontological Concepts Driven Information Extraction from Unstructured Text

In this paper a knowledge base concept driven named entity recognition (NER) approach is presented. The technique is used for information extraction from news articles and linking it with background concepts in knowledge base. The work specifically focuses on extracting entity mentions from unstructured articles. The extraction of entity mentions from articles is based on the existing concepts from DBPedia ontology, representing the knowledge associated with the concepts present in Wikipedia knowledge base. A collection of the Wikipedia concepts through structured DBpedia ontology has been extracted and developed. For processing of unstructured text, Dawn news articles have been scrapped, preprocessed and thereby a corpus has been built. The proposed knowledge base driven system shows that given an article, the system identifies the entity mentions in the text article and how they can automatically be linked with the concepts to the corresponding entity mentions representing their respective pages on Wikipedia. The system is evaluated on three test collections of news articles on politics, sports and entertainment domains. The experimental results in respect of entity mentions are reported. The results are presented as precision, recall and f-measure, where the precision of extraction of relevant entity mentions identified yields the best results with a little variation in percent recall and f-measures. Additionally, facts associated with the extracted entity mentions both in form of sentences and Resource Description Framework (RDF) triples are presented so as to enhance the user’s understanding of the related facts presented in the article.

A Bag of Concepts Approach for Biomedical Document Classification Using Wikipedia Knowledge*. Spanish-English Cross-language Case Study.

The ability to efficiently review the existing literature is essential for the rapid progress of research. This paper describes a classifier of text documents, represented as vectors in spaces of Wikipedia concepts, and analyses its suitability for classification of Spanish biomedical documents when only English documents are available for training. We propose the cross-language concept matching (CLCM) technique, which relies on Wikipedia interlanguage links to convert concept vectors from the Spanish to the English space. The performance of the classifier is compared to several baselines: a classifier based on machine translation, a classifier that represents documents after performing Explicit Semantic Analysis (ESA), and a classifier that uses a domain-specific semantic annotator (MetaMap). The corpus used for the experiments (Cross-Language UVigoMED) was purpose-built for this study, and it is composed of 12,832 English and 2,184 Spanish MEDLINE abstracts. The performance of our approach is superior to any other state-of-the art classifier in the benchmark, with performance increases up to: 124% over classical machine translation, 332% over MetaMap, and 60 times over the classifier based on ESA. The results have statistical significance, showing p-values < 0.0001. Using knowledge mined from Wikipedia to represent documents as vectors in a space of Wikipedia concepts and translating vectors between language-specific concept spaces, a cross-language classifier can be built, and it performs better than several state-of-the-art classifiers.

Detecting the association of health problems in consumer-level medical text

Consumers usually do not know the complicated links between related health problems. This fact may cause troubles when they wish to seek complete information regarding such problems. This study detects the associations among health problems by extending the meaning of health terms with methods based on the latent Dirichlet allocation (LDA) probability topic model, the Medical Subject Headings (MeSH) thesaurus structure and the Wikipedia concept mapping. The terms represented health problems are selected from and extended by the consumer-level medical text. The vocabulary is different between the consumer-level and the professional-level medical text. Thus, the findings can be easily understood by the general public and be suitable to consumer-oriented applications. The methods were evaluated in two ways: (1) correlation analysis with expert rating to show the overall performance and (2) P@ N to reflect the ability of detecting strong associations. The LDA topic-model-based method outperforms the other two types. The judgment incongruence between the best method and the expert ratings has been examined, and the evidence shows that the automatic method sometimes detects real associations beyond those identified by human experts.

A similarity-based framework for service repository integration

Nowadays, repositories of services are becoming increasingly useful in the management of many public and private service provider organizations. In order to make a repository an integrated representation of all services delivered in an organization, a unified representation is desirable. Since several repositories of services, each potentially characterized by heterogeneous and conflicting representations, may coexist in the same organization or in cooperating organizations, the need for service repository integration techniques is emerging. In this paper, we investigate the problem of integrating heterogeneous service repositories. We first provide a conceptual model for describing services and semantic relationships among them. Then, we define a multi-level similarity function that is able to discover similarities between services belonging to different repositories, and to suggest candidate relationships among services. The proposed function combines a simple keyword-based matching with a more complex semantic matching that exploits the Explicit Semantic Analysis technique for generating a representation of services based on Wikipedia concepts. These combined techniques are implemented in the SCAn (Service Correspondence Analyzer) framework that supports the human expert during the repository integration process. The framework has been evaluated in a real-life scenario and the results demonstrate the effectiveness of the proposed approach.