Types Of Entities Research Articles

Research on named entity recognition of adverse drug reactions based on NLP and deep learning.

Introduction: Adverse drug reactions (ADR) are directly related to public health and become the focus of public and media attention. At present, a large number of ADR events have been reported on the Internet, but the mining and utilization of such information resources is insufficient. Named entity recognition (NER) is the basic work of many natural language processing (NLP) tasks, which aims to identify entities with specific meanings from natural language texts. Methods: In order to identify entities from ADR event data resources more effectively, so as to provide valuable health knowledge for people, this paper introduces ALBERT in the input presentation layer on the basis of the classic BiLSTM-CRF model, and proposes a method of ADR named entity recognition based on the ALBERT-BiLSTM-CRF model. The textual information about ADR on the website "Chinese medical information query platform" (https://www.dayi.org.cn) was collected by the crawler and used as research data, and the BIO method was used to label three types of entities: drug name (DRN), drug component (COM), and adverse drug reactions (ADR) to build a corpus. Then, the words were mapped to the word vector by using the ALBERT module to obtain the character level semantic information, the context coding was performed by the BiLSTM module, and the label decoding was using the CRF module to predict the real label. Results: Based on the constructed corpus, experimental comparisons were made with two classical models, namely, BiLSTM-CRF and BERT-BiLSTM-CRF. The experimental results show that the F 1 of our method is 91.19% on the whole, which is 1.5% and 1.37% higher than the other two models respectively, and the performance of recognition of three types of entities is significantly improved, which proves the superiority of this method. Discussion: The method proposed can be used effectively in NER from ADR information on the Internet, which provides a basis for the extraction of drug-related entity relationships and the construction of knowledge graph, thus playing a role in practical health systems such as intelligent diagnosis, risk reasoning and automatic question answering.

Development and Study of a Knowledge Graph for Retrieving the Relationship Between BVDV and Related Genes

Background: Bovine viral diarrhea virus (BVDV) can cause diarrhea, abortion, and immunosuppression in cattle, imposing huge economic losses for the global cattle industry. The pathogenic and immune mechanisms of BVDV remain elusive. The development of a BVDV-gene knowledge base can provide clues to reveal the interaction of BVDV with host cells. However, the traditional method of manually establishing a knowledge base is time-consuming and inefficient. The method of developing a knowledge base based on deep learning has noticeably attracted scholars' attention recently. Objective: The study aimed to explore the substitution of deep learning for manual mining of BVDVrelated genes and to develop a knowledge graph of the relationship between BVDV and related genes. Methods: A deep learning-based biomedical knowledge graph development method was proposed, which used deep learning to mine biomedical knowledge, model BVDV and various gene concepts, and store data in a graphical database. First, the PubMed database was used as the data source and crawler technology to obtain abstract data on the relationship between BVDV and various host genes. Pretrained BioBERT model was used for biomedical named entity recognition to obtain all types of gene entities, and the pre-trained BERT model was utilized for relationship extraction to achieve the relationship between BVDV and various gene entities. Then, it was combined with manual proofreading to obtain structured triple data with high accuracy. Finally, the Neo4j graph database was used to store data and to develop the knowledge graph of the relationship between BVDV and related genes. Results: The results showed the obtainment of 71 gene entity types, including PRL4, MMP-7, TGIF1, etc. 9 relation types of BVDV and gene entities were obtained, including "can downregulate expression of", "can upregulate expression of", "can suppress expression of", etc. The knowledge graph was developed using deep learning to mine biomedical knowledge combined with manual proofreading, which was faster and more efficient than the traditional method of establishing knowledge base manually, and the retrieval of semantic information by storing data in graph database was also more efficient. Conclusion: A BVDV-gene knowledge graph was preliminarily developed, which provided a basis for studying the interaction between BVDV and host cells.

EFFICIENCY OF THE FINANCIAL MANAGEMENT OF THE MODERN ORGANIZATION

The relevance of the issue of the prospects for the development of financial management is due to the need for financial entities to look for ways to increase the level of forecasting stability in their activity in the conditions of instability in the temporary economic situation.In particular, it includes the implementation of both capital structure financing decisions and decisions on: profit growth policies; tactical financing policy such as initial public offering, financial restructuring and debt financing; short-term financial management, such as cash, inventory and receivables and others.In this regard, the main theoretical concepts for the formation of the financial policy of financial entities have been identified, by considering a certain temporary economic situation - after the Covid crisis and the subsequent inflation.The financial expression of the effectiveness of the applied financial management in the specified situation was examined.This implies determining the main categories of quality activity of financial structures.For this purpose, the definitions of the effectiveness and efficiency of financial management have been derived and adapted. The main differences in the two meaningful concepts, evaluating the activity of financial institutions, through a system of criteria and indicators, are specified.In addition, a research model is presented - a regression analysis of the inflation of the Republic of Bulgaria with a duration of 18 months and a regression equation is derived.A forecast of the inflationary trends of a type common to the country's economic entity with a duration of 6 months was carried out.On this basis, a method for determining the inflation coefficient has been derived, using a first-order equation and the slope, the tangent of the angle made with the abscissa axis and a certain point from the estimated inflation graphic part. With the help of financial mathematics, a practical example of applying strategies of financial entities to determine the effectiveness and mainly the efficiency in reaching the desired state of the said entity was solved.Conclusions and recommendations are made for reactions of a type of financial entity to reduce the negative consequences of sudden changes and sharp fluctuations of the business environment in the current temporary financial situation.

Вплив когнітивних викривлень на розвиток економіки

The article studies cognitive distortions (illusions) and the possibilities of using cognitive and emotional factors to make decisions by different market actors in conditions of uncertainty. The theoretical foundations of the irrational behavior of economic actors, based on cognitive or social reasons, are highlighted. The authors note that the functioning of the cognitive sphere of a person is often accompanied by certain errors that are scientifically attributed to cognitive distortions in the rational behavioral paradigm that cause distortions in the perception of reality. Based on the understanding that the behavior of the human brain is sufficiently rational, since its work aims to save resources, resulting in logical errors, in other words, cognitive distortions that are caused by limited cognitive resources, as well as external limiting factors or insufficient motivation. Therefore, it can be considered that since the brain uses cognitive illusions to save resources to accelerate decision making, said process has evolved evolutionarily in order to survive. It has been established that the inability of the human brain to fully process the entire huge body of information when making decisions and leads to the existence of cognitive distortions, which in turn can negatively affect not only the geopolitical situation in the world, but also cause the death of many other people, so it is necessary to thoroughly investigate their influence on the behavior of economic actors. The article explores two systems of thinking. In the I system, thinking is distinguished by the intuitiveness of the decisions made, the high speed of thought processes with their minimal awareness. In the II system, thinking is characterized by controllability, systematicity, rationality, that is, it is logically justified and conscious. Based on the characteristics of each of the systems, it is possible to understand how individuals make decisions and what were the subconscious reasons for a particular reaction. Factors affecting the behavior of individuals and the causes of cognitive distortions that can be taken into account when building economic incentives and even economic processes in general have been identified. The influence of the most faithful cognitive illusions on different types of economic entities is outlined. Proper diagnosis of cognitive distortions in the behavior of economic entities in business in the future will allow, with the help of proper influences, to transform it into the desired state.

Named Entity Recognition of Diabetes Online Health Community Data Using Multiple Machine Learning Models.

The rising prevalence of diabetes and the increasing awareness of self-health management have resulted in a surge in diabetes patients seeking health information and emotional support in online health communities. Consequently, there is a vast database of patient consultation information in these online health communities. However, due to the heterogeneity and incompleteness of the content, mining medical information and patient health data from these communities can be a challenge. To address this issue, we built the RoBERTa-BiLSTM-CRF (RBC) model for identifying entities in the online health community of diabetes. We selected 1889 question-answer texts from the most active online health community in China, Good Doctor Online, and used these public data to identify five types of entities. In addition, we conducted a comparative evaluation with three other commonly used models to validate the performance of our proposed model, including RoBERTa-CRF (RC), BilSTM-CRF (BC), and RoBERTa-Softmax (RS). The results showed that the RBC model achieved excellent performance on the test set, with an accuracy of 81.2% and an F1 score of 80.7%, outperforming the performance of traditional entity recognition models in named entity recognition in online medical communities for doctors and diabetes patients. The high performance of entity recognition in online health communities will provide a crucial knowledge source for constructing medical knowledge graphs. This integration would help alleviate the growing demand for medical consultations and the strain on healthcare resources, while assisting healthcare professionals in making informed decisions and providing personalized services to patients.

EduNER: a Chinese named entity recognition dataset for education research.

A high-quality domain-oriented dataset is crucial for the domain-specific named entity recognition (NER) task. In this study, we introduce a novel education-oriented Chinese NER dataset (EduNER). To provide representative and diverse training data, we collect data from multiple sources, including textbooks, academic papers, and education-related web pages. The collected documents span ten years (2012-2021). A team of domain experts is invited to accomplish the education NER schema definition, and a group of trained annotators is hired to complete the annotation. A collaborative labeling platform is built for accelerating human annotation. The constructed EduNER dataset includes 16 entity types, 11k+ sentences, and 35,731 entities. We conduct a thorough statistical analysis of EduNER and summarize its distinctive characteristics by comparing it with eight open-domain or domain-specific NER datasets. Sixteen state-of-the-art models are further utilized for NER tasks validation. The experimental results can enlighten further exploration. To the best of our knowledge, EduNER is the first publicly available dataset for NER task in the education domain, which may promote the development of education-oriented NER models.

Raising the Resilience of Industrial Manufacturers through Implementing Natural Gas-Fired Distributed Energy Resource Systems with Demand Response

The use of relatively small-scale distributed electric power generation sources is one of the key focus areas in the development of global industry and regional power generation. By integrating distributed generation sources into their on-site energy infrastructure, industrial consumers gain new characteristics and possibilities as entities of the power system that do not only consume power, but in fact can flexibly generate and deliver electricity to local and even centralized grids. This type of entity is called a distributed energy resource system with demand response (Russian: ‘active energy complex’). The purpose of this study is to lay the methodological foundation for the use of distributed energy resource systems with demand response in industrial sites under existing gas and power market conditions and for ensuring the synchronization of parameters that is necessary for managing complex energy consumption. This article provides an empirical study of the principles of the natural gas pricing under the demand volatility of regional markets and the Russian Mercantile Exchange. The article outlines the key drivers, as identified by the authors, that impact gas consumption by a distributed energy resource system, including demand characteristics, limitations and capacity of the gas network and the mode of gas consumption by an industrial enterprise and its generator. Accounting for all of these factors is essential for effective management and proper operational adjustment of a distributed energy resource system with demand response. The result of the study is a proprietary model and a tool for the management of distributed energy resource systems in integration with the gas demand management, which analyze the internal and external parameters of the industrial entity’s operations and its distributed energy resource system, as well as factors existing in the integrated distributed energy system where the consumer is able to buy natural gas in various market segments. The proprietary tool of distributed energy resource system management is based on the centralized control system, which combines performance analytics, operational scheduling of production and the distributed energy resource system, price planning for the wholesale and retail power markets, regional gas markets and exchange, monitoring all elements of the system, and assessment of different active energy management scenarios under various external and internal conditions impacting production and energy demand. Our proprietary tool has been successfully tested in a typical industrial site and was reported to deliver a significant electricity and gas cost-saving effect, which amounted to an 18 percent reduction in the total energy costs of the company, or more than USD 2.6 million per year. The resulting saving effect can recoup the costs of investing in a distributed energy resource system, including construction and installation of the local grid and automation infrastructure, and can be obtained in any country of the world.

Attention-based cross domain graph neural network for prediction of drug-drug interactions.

Drug-drug interactions (DDI) may lead to adverse reactions in human body and accurate prediction of DDI can mitigate the medical risk. Currently, most of computer-aided DDI prediction methods construct models based on drug-associated features or DDI network, ignoring the potential information contained in drug-related biological entities such as targets and genes. Besides, existing DDI network-based models could not make effective predictions for drugs without any known DDI records. To address the above limitations, we propose an attention-based cross domain graph neural network (ACDGNN) for DDI prediction, which considers the drug-related different entities and propagate information through cross domain operation. Different from the existing methods, ACDGNN not only considers rich information contained in drug-related biomedical entities in biological heterogeneous network, but also adopts cross-domain transformation to eliminate heterogeneity between different types of entities. ACDGNN can be used in the prediction of DDIs in both transductive and inductive setting. By conducting experiments on real-world dataset, we compare the performance of ACDGNN with several state-of-the-art methods. The experimental results show that ACDGNN can effectively predict DDIs and outperform the comparison models.

Structure Enhanced Path Reasoning for Knowledge Graph Completion

Knowledge graphs are crucial foundations for building intelligent systems, such as question answering and recommendation. However, their performance is hampered by the incompleteness of KGs, so the knowledge graph completion arises to infer whether a triple of the form (head entity, relation, tail entity) is a missing fact. The path-based approach that encodes paths from the head entity to the tail entity for reasoning achieves good performance. Previous work suggests that entity type is beneficial for learning path representations. Nevertheless, the semantics of entities are not captured accurately, as many entities are not typed or loosely typed. In addition, previous methods tend to model paths only from the forward direction but fail to capture new path patterns from the reverse direction (i.e., tail entity to head entity). In this paper, we introduce a structure enhanced path reasoning (SPR) framework to address the above-given problems. First, the model uilizes the structure of entities, i.e., their relational contexts (the relations linked from the given entity), to obtain a reliable path representation that captures correct entity semantics. This information is accessible to all nonisolated entities in all KGs, so that it can compensate the semantics for entities or KGs that have no type available. Second, we leverage the structure of paths to derive their reverse paths, so as to enhance the path representation by additionally encoding the new patterns embedded in them through a dual path encoding method. In order to verify the effectiveness of the proposed methods, we design different architectures based on LSTM and Transformer, respectively. Experimental results on two benchmark datasets, WN18RR, and FB15k-237, show that our approach apparently outperforms state-of-the-art methods on fact prediction task and relation prediction task. Furthermore, extensive experiments illustrate the benefits of enhancing path reasoning by exploiting structure information from entity relational contexts and the dual path encoding method.

Доказательное и профессиональное суждение в аудите

The article proposes and substantiates new formulations of the concepts of professional and evidence-based judgment. The concept of the application of such judgments when working with numerical estimates is developed. The usefulness of using the method of expert assessments in the audit is shown. Time series are built — in current and comparable prices — of average revenues for audits for audit organizations in general and in three sections: large-scale, regional, type of economic entities. Considered — both in general terms and with examples — the possibility of using the constructed time series through a combination of professional and evidence-based judgments when making various decisions in the audit. Suggestions for improving this combination are formulated. Th e possibility of combining professional and evidence-based judgments in assessing audit risks and in determining the size of audit samples is shown.

DanfeNER - Named Entity Recognition in Nepali Tweets

Twitter allows users to easily post tweets on any subject or event anytime, generating massive amounts of rich text content on diverse topics. Automated methods such as Named Entity Recognition (NER) are required to process the massive tweet data. Processing tweets, however, poses a special challenge as they are informal posts with incomplete context and often contain acronyms, hashtags, misspellings, abbreviations, and URLs due to length constraints. This paper presents the first systematic study of NER in Nepali tweets corresponding to five different entity types: Person Name (PER), Location (LOC), Organization (ORG), Date (DAT), and Event (EVT). We develop DanfeNER, the first human-labeled high-quality NER benchmark data sets for the low-resource language Nepali. DanfeNER contains 5,366 records and 3,463 entities in its train set and 2,301 records and 1,503 entities in its test set. Using this data set, we benchmark several state-of-the-art Nepali monolingual and multilingual transformer models, obtaining micro-averaged F1 scores up to 81%.

Imperial statehood as the basis for successful national development of Russia

This article is devoted to the study of imperial statehood as a traditional form of statehood for Russia and the Russian people. The author of the article notes that in the minds of most Russians and residents of the Earth, the term “empire” is perceived with a pronounced negative connotation, which is a consequence of the dominant in science and mass consciousness, thanks to the activities of the media and propaganda, certain myths about empire and ideological attitudes.Imperial states are usually identified either with a large power in their territorial possessions, or with a special type of state entities seeking constant territorial expansion, coupled with the merciless exploitation of “enslaved” peoples, i.e. with colonial powers, often to raise their status calling themselves “empires”.Meanwhile, such ideas have nothing to do with reality. Classical empires are a special type of state entity dominated by the idea of unity of society in the name of the common good. Different ethnic groups coexist peacefully in culture and customs, coexisting under the patronage and supervision of the core imperial ethnic group, while maintaining their traditional way of life, economic structures, the system of local self-government and often statehood.The study of the phenomenon of “empire” is very important at present in the light of determining the prospects and vector for the further development of the Russian world, Russian society and statehood. For, as history shows, the fate of the empire is inseparable from the fate of the core imperial ethnic group, i.e. the Russian people. And in this sense, the empire is not only a tradition, but also the fate of Russia.

AIONER: all-in-one scheme-based biomedical named entity recognition using deep learning.

Biomedical named entity recognition (BioNER) seeks to automatically recognize biomedical entities in natural language text, serving as a necessary foundation for downstream text mining tasks and applications such as information extraction and question answering. Manually labeling training data for the BioNER task is costly, however, due to the significant domain expertise required for accurate annotation. The resulting data scarcity causes current BioNER approaches to be prone to overfitting, to suffer from limited generalizability, and to address a single entity type at a time (e.g. gene or disease). We therefore propose a novel all-in-one (AIO) scheme that uses external data from existing annotated resources to enhance the accuracy and stability of BioNER models. We further present AIONER, a general-purpose BioNER tool based on cutting-edge deep learning and our AIO schema. We evaluate AIONER on 14 BioNER benchmark tasks and show that AIONER is effective, robust, and compares favorably to other state-of-the-art approaches such as multi-task learning. We further demonstrate the practical utility of AIONER in three independent tasks to recognize entity types not previously seen in training data, as well as the advantages of AIONER over existing methods for processing biomedical text at a large scale (e.g. the entire PubMed data). The source code, trained models and data for AIONER are freely available at https://github.com/ncbi/AIONER.

Metapaths: similarity search in heterogeneous knowledge graphs via meta-paths.

Heterogeneous knowledge graphs (KGs) have enabled the modeling of complex systems, from genetic interaction graphs and protein-protein interaction networks to networks representing drugs, diseases, proteins, and side effects. Analytical methods for KGs rely on quantifying similarities between entities, such as nodes, in the graph. However, such methods must consider the diversity of node and edge types contained within the KG via, for example, defined sequences of entity types known as meta-paths. We present metapaths, the first R software package to implement meta-paths and perform meta-path-based similarity search in heterogeneous KGs. The metapaths package offers various built-in similarity metrics for node pair comparison by querying KGs represented as either edge or adjacency lists, as well as auxiliary aggregation methods to measure set-level relationships. Indeed, evaluation of these methods on an open-source biomedical KG recovered meaningful drug and disease-associated relationships, including those in Alzheimer's disease. The metapaths framework facilitates the scalable and flexible modeling of network similarities in KGs with applications across KG learning. The metapaths R package is available via GitHub at https://github.com/ayushnoori/metapaths and is released under MPL 2.0 (Zenodo DOI: 10.5281/zenodo.7047209). Package documentation and usage examples are available at https://www.ayushnoori.com/metapaths.

Cyberthreats and Healthcare

Introduction:Cyberattacks against healthcare have been growing at an alarming rate globally targeting the theft of clinical research intellectual property, personally identifiable information, and personal health information. Recent studies have also shown a concerning correlation between cyberattacks and patient morbidity and mortality rates. Many top security experts consider cyberattacks a top national security concern.This paper is a descriptive analysis of healthcare-related breaches in the United States in the past decade and an analysis of cybersecurity threats that are currently facing the industry.Method:Breach reports of unsecured protected health information affecting 500 or more individuals in the US are publicly accessible through the U.S. Department of Health and Human Services Office for Civil Rights portal. The database was downloaded and searched for all reported breaches occurring between January 1, 2011 - December 31, 2021. Breaches were subdivided by states, dates, location, entity type, and individuals affected.Results:Of the 3,822 PHI breaches recorded, 1,593 (41.7%) were hacking/IT related, 1,055 (27.6%) were listed as unknown, 819 (21.4%) were theft related, 194 (5.1%) were loss related, 97 (2.5%) were related to improper disposal and 64 (1.7%) were listed as “others.”Breaches occurred within the main categories as follows: network server (957 [25%]), email (877 [23%]), paper/films (665 [17%]), other (454 [12%]), laptop (341 [9%]), desktop (309 [8%]), and electronic medical records (220 [6%]).Conclusion:A total of 3,822 breaches affecting 283,335,803 people in the United States were recorded from January 1, 2011 to December 31, 2021.The most reported breaches were from healthcare providers with 2,827 (75.1%) events, followed by health plans (500 [13.1%]), business associates (480 [12.6%]) and healthcare clearinghouses (10 [0.3%]). 4 (0.1%) breaches were from unknown sources.This report may help healthcare providers understand the extent of the issue and mitigate some of the associated risks.

TaughtNet: Learning Multi-Task Biomedical Named Entity Recognition From Single-Task Teachers.

In Biomedical Named Entity Recognition (BioNER), the use of current cutting-edge deep learning-based methods, such as deep bidirectional transformers (e.g. BERT, GPT-3), can be substantially hampered by the absence of publicly accessible annotated datasets. When the BioNER system is required to annotate multiple entity types, various challenges arise because the majority of current publicly available datasets contain annotations for just one entity type: for example, mentions of disease entities may not be annotated in a dataset specialized in the recognition of drugs, resulting in a poor ground truth when using the two datasets to train a single multi-task model. In this work, we propose TaughtNet, a knowledge distillation-based framework allowing us to fine-tune a single multi-task student model by leveraging both the ground truth and the knowledge of single-task teachers. Our experiments on the recognition of mentions of diseases, chemical compounds and genes show the appropriateness and relevance of our approach w.r.t. strong state-of-the-art baselines in terms of precision, recall and F1 scores. Moreover, TaughtNet allows us to train smaller and lighter student models, which may be easier to be used in real-world scenarios, where they have to be deployed on limited-memory hardware devices and guarantee fast inferences, and shows a high potential to provide explainability. We publicly release both our code on github1 and our multi-task model on the huggingface repository.2.

Securities as Capital Deposit in the Establishment of Limited Liability Company

There are various types of business entities in Indonesia, namely divided into non-legal entities and legal entities. One of which frequently chosen by the business actor is a limited liability company (PT) due to its limited liability which only need to provide a capital that has separate assets between private ownership and the company. To establish a Limited Liability Company, the Company will need a Capital Deposit to run the business. Usually, the capital is paid in cash. The research aims to determine whether the capital deposit required to establish a limited liability company can be paid using a method other than Cash. The research is using a normative legal research by using statute and library approach. The research findings reveal that according to Article 34 paragraph (1), the capital deposit can be made in Cash and/or other forms. It means if the Capital Deposit, which is paid in other forms, can be valued in money, and accepted, as well as approved, by the Company’s founders. Payment of shares in securities must be announced, at least, in 1 (one) newspaper or more within 14 (fourteen) days after the deed of establishment is signed or after the General Meeting of Shareholders decides on the payment of shares.

A Framework To Make Voting System Transparent Using Blockhain Technology

Generally, governments release schemes or plans like roadways or industries to some area as different projects. During this process, different types of peoples will be there as supportive or opponent for the schemes. In this project, we presented a secure and transparent framework for government schemes using blockchain. Blockchain is used as a secure and immutable data structure to store the government records that are highly susceptible to tampering. Here, we aim to address these issues to build a transparent and secure edge computing infrastructure for the allocation of government schemes which not only eliminates the need for human supervision or intervention but also makes it easy for the government to keep track and update its policies as time progresses. To solve this issue, we propose the framework to use blockchain technology for creating a decentralized system to perform government scheme processes with ease, transparent, auditable, and immutable. The proposed model consists of a decentralized consortium architecture that combines both the security and privacy of a Permissioned Blockchain and the openness and transparency of a Permission-less Blockchain. The target of the model is to efficiently handle the government tender process securely. The system mainly consists of three types of entities: government officials, citizens and schemes.

CORRUPCION IN THE ELECTION PROCESS

The purpose and tasks of the research are explained in the introductory part of the article. The comparative qualitative study of monographs and scientific articles published on this topic is selected as the research methodology. Electoral corruption is a socio-negative phenomenon that distorts real political competition and involves the use of status and official position during the election process, the preparation and holding of the referendum, and the illegal receipt of benefits for personal or group interests. Also, the promise of providing such benefits and benefits. In the introductory part of the article, it is emphasized that a generally accepted conceptual apparatus has not yet been established, which would characterize any corrupt relationship within the framework of the elections and election campaign. Researchers do not have a unified opinion about the corruption in the field of electoral relations, on the definition of its content, as well as on its signs, subjects, and forms of existence. Corruption is partly facilitated by a bureaucratic system of governance. It is also associated with the type of cultural orientation (collectivism and individualism). In the main part of the article, a certain combination of signs of corruption in the electoral process is revealed, which distinguishes it from other similar ones. These signs are the sphere of existence; a certain list of entities; the use of their status, and the official position by the subjects of the election process; a goal characteristic of this type of corrupt relationship. The article describes the goals of this type of corrupt entity. In the final part of the article, it is emphasized that corruption in the election process prevents the establishment of Georgia as a democratic, legal state with a developed civil society.

Decomposed Two-Stage Prompt Learning for Few-Shot Named Entity Recognition

Named entity recognition (NER) in a few-shot setting is an extremely challenging task, and most existing methods fail to account for the gap between NER tasks and pre-trained language models. Although prompt learning has been successfully applied in few-shot classification tasks, adapting to token-level classification similar to the NER task presents challenges in terms of time consumption and efficiency. In this work, we propose a decomposed prompt learning NER framework for few-shot settings, decomposing the NER task into two stages: entity locating and entity typing. In training, the location information of distant labels is used to train the entity locating model. A concise but effective prompt template is built to train the entity typing model. In inference, a pipeline approach is used to handle the entire NER task, which elegantly resolves time-consuming and inefficient problems. Specifically, a well-trained entity locating model is used to predict entity spans for each input. The input is then transformed using prompt templates, and the well-trained entity typing model is used to predict their types in a single step. Experimental results demonstrate that our framework outperforms previous prompt-based methods by an average of 2.3–12.9% in F1 score while achieving the best trade-off between accuracy and inference speed.