Future of information retrieval systems and the role of library and information science experts in their development

Many organizations and businesses are using futurology to keep pace with the ever-increasing changes in the world, as the businesses and organizations need to be updated to achieve organizational and business growth and development. A review of the previous studies has shown that no systematic research has been already conducted on the future of information retrieval systems and the role of library and information science experts in the future of such systems. Therefore, a qualitative study was conducted by reviewing resources, consulting experts, doing interaction analysis, and writing scenarios. The results demonstrated 13 key factors affecting the future of information retrieval systems in the form of two driving forces of social determinism and technological determinism, and four scenarios of Canopus star, Ursa major, Ursa minor, and single star. The results also showed the dominance of technology and social demand and its very important role in the future of information retrieval systems.

Compilation and evaluation of the Spanish SatiCorpus 2021 for satire identification using linguistic features and transformers

Satirical content on social media is hard to distinguish from real news, misinformation, hoaxes or propaganda when there are no clues as to which medium these news were originally written in. It is important, therefore, to provide Information Retrieval systems with mechanisms to identify which results are legitimate and which ones are misleading. Our contribution for satire identification is twofold. On the one hand, we release the Spanish SatiCorpus 2021, a balanced dataset that contains satirical and non-satirical documents. On the other hand, we conduct an extensive evaluation of this dataset with linguistic features and embedding-based features. All feature sets are evaluated separately and combined using different strategies. Our best result is achieved with a combination of the linguistic features and BERT with an accuracy of 97.405%. Besides, we compare our proposal with existing datasets in Spanish regarding satire and irony.

A Scalable Real Time Agent-Based Information Retrieval Engine

In distributed information retrieval systems, information in web should be ranked based on a combination of multiple features. Linear combination of ranks has been the dominant approach due to its simplicity and efficiency. Such a combination scheme in distributed infrastructure requires that ranks in resources or agents are comparable to each other. The main challenge is how to transform the raw rank values of different criteria appropriately to make them comparable before any combination. In this manuscript, we will demonstrate how to rank Web documents based on its resource-provided information stream and how to combine and incorporate several raking schemas in one time. The system was tested on the queries provided by a Text Retrieval Conference (TREC), and our experimental results showed that it is robust and efficient compared with similar platforms that used offline data resources.

Linguistic support of library IPS of the National Library of Ukraine named after Yaroslav the Wise: analysis of scientific and methodological activities of the applied unit

The purpose of the article is to analyze traditional quantitative bibliometric indicators to assess theresults of scientific and methodological activities of the Department of Linguistic Support of InformationSearch Systems of the Yaroslav Mudryi National Library of Ukraine for 2017-2021, present quantitative andqualitative characteristics of this area of research. The methodological basis is centered the representationof scientific and methodological activities of the National Library is bibliometric analysis, which involves thestudy of basic statistical and bibliographic indicators of a particular area of rk with quantitative, qualitativedata, information analysis, and synthesis of semantic features of content and bibliographic data. The scientificnovelty consists in the complex bibliometric analysis of the scientific and methodical activity of the applieddepartment of the National Library and estimation of own potential and definition of prospects of developmentof this direction of activity of division. Conclusions. Solving applied problems of linguistic support of libraryinformation retrieval systems is accompanied by appropriate scientific and methodological activities. Byrepresenting the main object of study in bibliometric research is the dynamics of publishing activity in agiven period, the published works of specialists of the department were grouped by characteristics: authors,thematic sections, types of publications, periodicals, and more. One of the areas of bibliometric research wasthe separation of the total number of publications that are co-authored and created in collaboration withexperts from other institutions. In general, the material presented in the article allows identifying problematicaspects of scientific and methodological activities of the applied department of the library and promisingareas of development in the linguistic support of library information retrieval systems. The use of bibliometricanalysis techniques for certain areas of library work contributes to the improvement of management processesin applied areas of libraries.Keywords: library, information retrieval systems, linguistic support, scientific and methodical activity,bibliometric analysis.

You Don’t Need Labeled Data for Open-Book Question Answering

Open-book question answering is a subset of question answering (QA) tasks where the system aims to find answers in a given set of documents (open-book) and common knowledge about a topic. This article proposes a solution for answering natural language questions from a corpus of Amazon Web Services (AWS) technical documents with no domain-specific labeled data (zero-shot). These questions have a yes–no–none answer and a text answer which can be short (a few words) or long (a few sentences). We present a two-step, retriever–extractor architecture in which a retriever finds the right documents and an extractor finds the answers in the retrieved documents. To test our solution, we are introducing a new dataset for open-book QA based on real customer questions on AWS technical documentation. In this paper, we conducted experiments on several information retrieval systems and extractive language models, attempting to find the yes–no–none answers and text answers in the same pass. Our custom-built extractor model is created from a pretrained language model and fine-tuned on the the Stanford Question Answering Dataset—SQuAD and Natural Questions datasets. We were able to achieve 42% F1 and 39% exact match score (EM) end-to-end with no domain-specific training.

PERSON-ORIENTED APPROACH TO FORMING SCIENTIFIC AND RESEARCH COMPETENCE OF FUTURE ENVIRONMENTALISTS

In the course of the research the theoretical and practical development of the problem of a person-oriented approach to the formation of research and development competence was analyzed. The research was conducted using a systemic synergistic approach, using general scientific methods of analysis, syn-thesis and comparison. The essence of the concepts of "person-oriented learning", " person-oriented approach" is revealed. Conditions and methods of organization of the educational process during the formation of the scientific and research competence from the standpoint of person-oriented approach are considered. It is determined that the use of developed information retrieval systems and computer tools in the educational process realizes the principles of scientific, professional orientation, practical significance and creates the necessary conditions for the implementation of an individual, differentiated person-oriented approach in the formation of research and development competence. An example of the application of a person-oriented approach in the formation of the research competence of future environmental specialists is provided with the help of the developed information-retrieval system of the purification equipment, which allows forming integrative knowledge from ecology and other branches of knowledge. The results of the research may form the basis for further scientific analysis - the development of theoretical and methodological foundations for the formation of scientific research competence of future specialists-ecologists.

Transliteration: A Magnetic Analysis

Machine transliteration is an important problem in an increasingly multilingual world as it plays a critical role in many downstream applications such as machine translation or cross-lingual information retrieval systems. There is now a vast amount of information accessible via the Internet where a lot of regional and cultural information is put on the World Wide Web in different languages and scripts. There are more that six thousand living languages in the world. Adding to the diversity is the fact that some languages are written in different scripts in different regions of the world. The multitude of foreign languages and mutually incomprehensible scripts of the same language pose a barrier to information exchange as we cannot all learn every language or script in use worldwide. Therefore, if we can get around the language barrier or at least the script barrier, we can access much more of the world's culture and can explore its abundant richness. Keywords: Transliteration, Translation. Cross-lingual, Multilingual, Language, Script

A Platform for Keyword Search and its Application for COVID-19 Pandemic Data

Keyword search is typically associated with information retrieval systems. However, recently, keyword search has been expanded to relational databases and RDF datasets, as an attractive alternative to traditional database access. This paper introduces DANKE, a platform for keyword search over databases, and discusses how third-party applications can be equipped with DANKE to take advantage of a data retrieval mechanism that does not require users to have specific technical skills for searching, retrieving and exploring data. The paper ends with the description of an application, called CovidKeyS, which uses DANKE to implement keyword search over three COVID-19 data scenarios.