Information Retrieval Technology Research Articles

Assessing Large-Scale, Cross-Domain Knowledge Bases for Semantic Search

Semantic Search refers to set of approaches dealing with usage of Semantic Web technologies for information retrieval in order to make the process machine understandable and fetch precise results. Knowledge Bases (KB) act as the backbone for semantic search approaches to provide machine interpretable information for query processing and retrieval of results. These KB include Resource Description Framework (RDF) datasets and populated ontologies. In this paper, an assessment of the largest cross-domain KB is presented that are exploited in large scale semantic search and are freely available on Linked Open Data Cloud. Analysis of these datasets is a prerequisite for modeling effective semantic search approaches because of their suitability for particular applications. Only the large scale, cross-domain datasets are considered, which are having sizes more than 10 million RDF triples. Survey of sizes of the datasets in triples count has been depicted along with triples data format(s) supported by them, which is quite significant to develop effective semantic search models.

The Development of a State-Aware Equipment Maintenance Application Using Sensor Data Ranking Techniques.

Billions of electric equipment are connected to Internet of Things (IoT)-based sensor networks, where they continuously generate a large volume of status information of assets. So, there is a need for state-aware information retrieval technology that can automatically recognize the status of each electric asset and provide the user with timely information suitable for the asset management of electric equipment. In this paper, we investigate state-aware information modeling that specializes in the asset management of electric equipment. With this state-aware information model, we invent a new asset state-aware ranking technique for effective information retrieval for electric power and energy systems. We also derive an information retrieval scenario for IoT in power and energy systems and develop a mobile application prototype. A comparative performance evaluation proves that the proposed technique outperforms the existing information retrieval technique.

Query reformulation approach using domain specific ontology for semantic information retrieval

Conventional search engines provide a lot of irrelevant results to the user’s search query, which consumes a lot of time and effort, as the context and semantics of the request made by the user are not analyzed to the optimum extent. This highlights for the need of a methodology embedded in the search machinery, enabling semantic web search. Ontologies have proven to be an effective technology for such semantic knowledge representation and information retrieval. In this research paper, the researcher has constructed a string ontology in a new domain (the music domain) from scratch using Protege 5.0 for semantic information retrieval for a query in the search engine. This ontology is further used in the proposed ontology based semantic information retrieval method (OBSIRM), which has been built to refine the web search in the music domain. The researcher has proposed a novel approach to refine the web search in which the query is first replaced with abbreviations along with the use of the multilingual concept to search a query. The results of the proposed method have been compared with Google. The accuracy and efficiency of the proposed method has been measured in terms of precision and recall. The average precision and recall of OBSIRM is 1.43 and 0.7 as compared to generic Google search engine i.e. 1.04 and 0.51. Hence it can safely be concluded that in the domain of research the OBSIRM performs better in terms of users’ expectations than Google (for string instrument domain considered by the researcher) as far as relevant information retrieval is concerned.

Improving software bug-specific named entity recognition with deep neural network

There is a large volume of bug data in the bug repository, which contains rich bug information. Existing studies on bug data mining mainly rely on using information retrieval (IR) technology to search relevant historical bug reports. These studies basically treat a bug report as a closed unit, ignoring the semantic and structural information within it. Named-entity recognition (NER) is an important task of information extraction (IE) technology. Based on NER, fine-grained factual information could be comprehensively extracted to further form structured data, which provides a new way to improve the accessibility of bug information. However, bug NER is different from general NER tasks. Bug reports are free-form text, which include a mixed language environment studded with code, abbreviations and software-specific vocabularies. In this paper, we propose a deep neural network approach for bug-specific entity recognition called DBNER using bidirectional long short-term memory (LSTM) with Conditional Random Fields decoding model (CRF). DBNER extracts multiple features from the massive bug data and uses attention mechanism to improve the consistency of entity tags in the bug reports. Experiment results show that the F1-score reaches an average of 91.19%. In addition, in cross-project experiments, the DBNER’s F1-score reaches an average of 84%.

Probability model of sensitive similarity measures in information retrieval

In today’s Internet age, a lot of data is stored and used, which is very important. In people’s daily life, if these data are sorted, information retrieval technology will be used, and in information retrieval, some information retrieval inaccuracies often appear. Information retrieval model is an important framework and method for fast, complete, and accurate user information retrieval. With the rapid development of information technology, great changes have taken place in people’s production and life. Various information network technologies are widely used in people’s lives. The resulting flow of information shows explosive growth, information retrieval. User requirements are getting higher and higher. How to complete personalized information retrieval in a large amount of mixed information, so that retrieval technology can help us obtain effective retrieval results, has become a realistic problem worth exploring. In this article, the application of probability model based on sensitive similarity measure in information retrieval model is analyzed, and a similarity measure algorithm based on spectral clustering is proposed. By improving the similarity measure, the sensitivity problem of scale parameters is overcome and the retrieval precision is improved. In order to better reflect the superiority of the proposed algorithm, this article compares with ng-jordan-weiss (NJW) and deep sparse subspace clustering (DSSC) algorithms. The experimental results show that the proposed algorithm is superior to NJW and DSSC algorithms for different data sets in different evaluation indicators (Rand and F-measure).

Lucene-P2: A Distributed Platform for Privacy-Preserving Text-based Search.

Information retrieval (IR) plays an essential role in daily life. However, currently deployed IR technologies, e.g., Apache Lucene - open-source search software, are insufficient when the information is protected or deemed to be private. For example, submitting a query to a publicly available search engine (e.g., Bing or Google) requires disclosing potentially delicate facts (e.g., thoughts about abortion), as well as the websites the user considers interesting. Similarly, when a private database contains sensitive information needed by the user, it cannot be searched freely. Over the past decade, various approaches, generally referred to as private information retrieval, have been proposed to obfuscate queries and responses, but they are limited in that the retrieved information is inadequate to compute relevancy. To address such limitations, this paper introduces the necessary techniques to build Lucene-P2 that allows one party to discover whether a second party harbors any relevant textual information without either party disclosing any information.

Research on We—Media Information Retrieval Technology of Knowledge Map

As the development direction of information retrieval technology gradually evolves toward the relationship of search entities, traditional relational databases are difficult to satisfy, and graph databases are specifically created to handle the relationships between data. This article explains the basic concept of graph database, and takes the example of domain-specific database information retrieval as an example, analyzes its advantages and disadvantages, and analyzes the challenges faced by the graph database in full-text information retrieval.

A Novel Class-Center Vector Model for Text Classification Using Dependencies and a Semantic Dictionary

Automatic text classification is a research focus and core technology in information retrieval and natural language processing. Different from the traditional text classification methods (SVM, Bayesian, KNN), the class-center vector method is an important text classification method, which has the advantages of less calculation and high efficiency. However, the traditional class-center vector method for text classification has the disadvantages that the class vector is large and sparse, and its classification accuracy is not high because of the lack of semantic information. To overcome these problems, this paper proposes a novel class-center vector model for text classification using dependencies and a semantic dictionary. We respectively use WordNet English semantic dictionary and Tongyici Cilin Chinese semantic dictionary to cluster the English or Chinese feature words in the class-center vector and to significantly reduce the dimension of class-center vector, thereby realizing a new class-center vector for text classification using dependencies and a semantic dictionary. Experiments show that, compared with traditional text classification algorithms, the improved class-center vector method has lower time complexity and higher accuracy on the 20Newsgroups English corpus, Fudan and Sogou Chinese corpus. This paper is an improved version of our NLPCC2019 conference paper.

A supervised term ranking model for diversity enhanced biomedical information retrieval

BackgroundThe number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle the problem. However, information needs cannot be completely satisfied by directly introducing the existing information retrieval techniques. Therefore, biomedical information retrieval not only focuses on the relevance of search results, but also aims to promote the completeness of the results, which is referred as the diversity-oriented retrieval.ResultsWe address the diversity-oriented biomedical retrieval task using a supervised term ranking model. The model is learned through a supervised query expansion process for term refinement. Based on the model, the most relevant and diversified terms are selected to enrich the original query. The expanded query is then fed into a second retrieval to improve the relevance and diversity of search results. To this end, we propose three diversity-oriented optimization strategies in our model, including the diversified term labeling strategy, the biomedical resource-based term features and a diversity-oriented group sampling learning method. Experimental results on TREC Genomics collections demonstrate the effectiveness of the proposed model in improving the relevance and the diversity of search results.ConclusionsThe proposed three strategies jointly contribute to the improvement of biomedical retrieval performance. Our model yields more relevant and diversified results than the state-of-the-art baseline models. Moreover, our method provides a general framework for improving biomedical retrieval performance, and can be used as the basis for future work.

Frequent itemset-based feature selection and Rider Moth Search Algorithm for document clustering

Document clustering has recently been paid great attention in retrieval, navigation, and summarization of huge volumes of documents. With a better document clustering approach, computers can organize a document corpus automatically to a meaningful cluster for enabling efficient navigation, and browsing of the corpus. Document navigation and browsing is a valuable complement to the deficiencies of information retrieval technologies. This paper introduces Modsup-based frequent itemset and Rider Optimization-based Moth Search Algorithm (Rn-MSA) for clustering the documents. At first, the input documents are given to the pre-processing step, and then, the extraction is carried out based on TF-IDF and Wordnet features. Once the extraction is done, the feature selection is carried out based on frequent itemset for the establishment of feature knowledge. At last, the document clustering is done using the proposed Rn-MSA, which is designed by combining Rider Optimization Algorithm (ROA), and the Moth Search Algorithm (MSA). The performance of the document clustering based on proposed Modsup + Rn-MSA is evaluated in terms of precision, recall, F-Measure, and accuracy. The developed document clustering method achieves the maximal precision of 95.90%, maximal recall of 96.41%, maximal F-Measure of 96.41%, and the maximal accuracy of 95.12% that indicates its superiority.

Research on the Private Customized Information Retrieval based on Hadoop Cluster

With the development of science and technology, it is no longer a technical difficulty for users to find the answers they need from massive data of information retrieval. At present, with information retrieval methods, the most urgent need is how to find personalized search results that satisfy users and meet their needs. Therefore, private customized information retrieval technology has great research value. This paper builds a Hadoop distributed cluster search engine, improves the PageRank algorithm, adds classified attributes such as user tone, and further classifies and ranks the web pages. At the same time, the C4.5 algorithm is used to classify users, thus it provides private customized search service. Through comparative experimental analysis, it is proved that the improved method proposed in this paper is effective and has profound research value.

Research on Library Information Visualization Retrieval Technology Based on Readers’ Needs

With the advancement of social informatization and the widespread application of network, the resources accumulated by libraries are becoming larger and larger. In addition to the need to store, transmit, retrieve and classify massive data, there is an urgent need to understand the relationship between data and its development trend. With the continuous development of modern information technology, digital libraries have also made great progress. And to introduce visual information retrieval technology into digital libraries is an inevitable trend in the future development. This paper first analyses the characteristics of readers’ information retrieval needs in the new period, and then introduce library information visual presentation technologies to design the library information resource visualization retrieval system. The system can visually display the collection structure, popular books, readers’ interests and so on, to truly reflect the structure, coverage, utilization and other indicators of books resource, and provide convenience for the visual sharing of library information resources.

Research on Semantic Information Retrieval Model of Bamboo Rattan Domain Based on Semantic Relevance

At present, the research of semantic information retrieval technology is mostly in the initial stage, and the research is mostly in exploratory theoretical research. Among them, the construction of domain semantic information retrieval model is still immature. In this paper, bamboo rattan field was selected as the research object, and the key problems in semantic information retrieval technology of bamboo rattan domain were analyzed. Based on the domain ontology of bamboo and rattan, the weight calculation method of bamboo rattan domain terms is defined. This paper introduces semantic relevance degree extension into the domain semantic information retrieval model of bamboo rattan, constructs a domain semantic information retrieval model suitable for bamboo rattan, and realizes the association retrieval and semantic query extension of text information in bamboo rattan domain.

Exploring How Evidence is Used in Care Through an Organizational Ethnography of Two Teaching Hospitals.

BackgroundNumerous published articles show that clinicians do not follow clinical practice guidelines (CPGs). However, a few studies explore what clinicians consider evidence and how they use different forms of evidence in their care decisions. Many of these existing studies occurred before the advent of smartphones and advanced Web-based information retrieval technologies. It is important to understand how these new technologies influence the ways clinicians use evidence in their clinical practice. Mindlines are a concept that explores how clinicians draw on different sources of information (including context, experience, medical training, and evidence) to develop collectively reinforced, internalized tacit guidelines.ObjectiveThe aim of this paper was to explore how evidence is integrated into mindline development and the everyday use of mindlines and evidence in care.MethodsWe draw on ethnographic data collected by shadowing internal medicine teams at 2 teaching hospitals. Fieldnotes were tagged by evidence category, teaching and care, and role of the person referencing evidence. Counts of these tags were integrated with fieldnote vignettes and memos. The findings were verified with an advisory council and through member checks.ResultsCPGs represent just one of several sources of evidence used when making care decisions. Some forms of evidence were predominately invoked from mindlines, whereas other forms were read to supplement mindlines. The majority of scientific evidence was accessed on the Web, often through smartphones. How evidence was used varied by role. As team members gained experience, they increasingly incorporated evidence into their mindlines. Evidence was often blended together to arrive at shared understandings and approaches to patient care that included ways to filter evidence.ConclusionsThis paper outlines one way through which the ethos of evidence-based medicine has been incorporated into the daily work of care. Here, multiple Web-based forms of evidence were mixed with other information. This is different from the way that is often articulated by health administrators and policy makers whereby clinical practice guideline adherence is equated with practicing evidence-based medicine.

Searching Data: A Review of Observational Data Retrieval Practices in Selected Disciplines.

A cross‐disciplinary examination of the user behaviors involved in seeking and evaluating data is surprisingly absent from the research data discussion. This review explores the data retrieval literature to identify commonalities in how users search for and evaluate observational research data in selected disciplines. Two analytical frameworks, rooted in information retrieval and science and technology studies, are used to identify key similarities in practices as a first step toward developing a model describing data retrieval.

Report on the DATA

The increasing availability of structured data on the web makes searching for data an important and timely topic. This report presents the motivation, output, and research challenges of the second DATA:SEARCH workshop which was held in conjunction with SIGIR 2018, in Ann Arbor, Michigan. This workshop explored challenges in data search, with a particular focus on data on the web. The aim was to share and establish links between different perspectives on search and discovery for different kinds of structured data, which can potentially inform the design of a wide range of information retrieval technologies. The DATA:SEARCH workshop tries to bring together communities interested in making the web of data more discoverable, easier to search and more user friendly.

Application of Ontology in the Web Information Retrieval

In this paper, the research advances of ontology and its application are reviewed firstly. With the development of ontology technology, subject-oriented web information retrieval technology combining ontology has been becoming one of the hot scientific issues. The innovative method of the semantic web technology combined with the traditional information retrieval technology is put forward, and the related algorithm based on ontology for judging the relevancy with different topics is also represented, and has proved to be effective in given experiments.

Study of Named Entity Recognition methods in biomedical field

Natural Language Processing (NLP) is very important in modern data processing taking into consideration different sources, forms and purpose of data as well as information in different areas our industry, administration, public and private life. Our studies concern Natural Language Processing techniques in biomedical field. The increasing volume of information stored in medical health record databases both in natural language and in structured forms is creating increasing challenges for information retrieval (IR) technologies. The paper presents the comparison study of chosen Named Entity Recognition techniques for biomedical field.

Mobile Phone Recommender System Using Information Retrieval Technology by Integrating Fuzzy OWA and Gray Relational Analysis

With the advancement and diversification of information retrieval technology, such technology has been widely applied in recent years in personalized information recommender systems (RSs) and e-commerce RSs in addition to data-mining applications, especially with respect to mobile phone purchases. By integrating the weights of fuzzy ordered weighted averaging (OWA) and gray relational analysis, this research calculated the recommended F1 indices of three weight calculation methods to be 20.5%, 14.36%, and 16.43% after an examination by 30 experimenters. According to the operational results attained by the 30 experimenters, the recommended products obtained by the fuzzy OWA and gray relational analysis calculation method covered the products recommended by the other two weight calculation methods with a higher recommendation effect.

The total archive: Data, subjectivity, universality

The complete system of knowledge is a standard trope of science fiction, a techno-utopian dream and an aesthetic ideal. It is Solomon’s House, the Encyclopaedia and the Museum. It is also an ideology – of Enlightenment, High Modernism and absolute governance. Far from ending the dream of a total archive, 20th-century positivist rationality brought it ever closer. From Paul Otlet’s ‘Mundaneum’ to Mass-Observation, from the Unity of Science movement to Wikipedia, the dream of universal knowledge dies hard. As a political tool, the total archive encompasses population statistics, gross domestic product, indices of the Standard of Living and the international ideology of the United Nations Educational, Scientific and Cultural Organization, the World Health Organization, the free market and, most recently, Big Data. Questions of the total archive engage key issues in the philosophy of classification, the poetics of the universal, the ideology of surveillance and the technologies of information retrieval. What are the social structures and political dynamics required to sustain total archives, and what are the temporalities implied by such projects? This introduction and the articles that follow describe and place in historical context a series of concrete instances of totality. Our analysis is arranged according to four central themes: the relationship between the Archive (singular) and archives (plural); the image of the archive and the aesthetics of totality; pathologies of accumulation; and the specific historical trajectory of the total archive in the 19th and 20th centuries.