Search

Semantic search encompasses advanced technological approaches to information discovery and retrieval, employing semantic techniques to extract information from intricately structured data sources. An effective search engine must have the ability of accessing and retrieving information of interest by employing reasoning with conceptual models. However, the structural and semantic information intrinsic in conceptual models is not readily amenable to reasoning and AI-enhanced semantic processing. Therefore, the chosen model should enable understanding the meaning of concepts and the relationships between them. Il should also carefully consider the context of the search, ultimately enhancing the accuracy of the returned results. Among the models that fulfill these objectives, conceptual graphs stand out as particularly interesting. They are built upon a robust theoretical framework that spans multiple domains, including philosophical, psychological, linguistic, and artificial intelligence disciplines. In this paper, we describe a method for semantic search driven by conceptual graph-based representation, and a powerful matching reasoning supported by a projection operation between the semantic annotations associated with the document and the submitted query. [ABSTRACT FROM AUTHOR]

Traditional searchable encryption constructions are often based on Term-Frequency and Inverse Document Frequency (TF-IDF) to retrieve relevant documents. These vectors are sensitive to the document length, sparse and lacks semantic understanding. Additionally, to address the growing privacy challenges, we propose pbins a novel design for achieving privacy preserving semantic-aware multi-keyword ranked search over encrypted data using “Private bins”. pbins is a method-agnostic encapsulation designed for indexes based on vector embeddings, enabling document retrieval without compromising privacy. Our approach leverages SBERT (Sentence-BERT) like Transformers to capture semantically meaningful sentence embeddings. The private bins group semantically similar documents together based on relevance scores thus allowing users to retrieve information without compromising data confidentiality. Private Bins can be updated dynamically without requiring a complete index reconstruction or uploading new structures to the cloud. Furthermore, pbins supports range-encoded and ranked search allowing users to retrieve the top-k documents efficiently while preserving privacy. The robustness of our approach is substantiated through a thorough security analysis that demonstrates correctness and forward privacy. Experiments on real-world news group dataset demonstrates the performance of pbins in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

The aim of this study was to develop a semantic search system for Khmer stone castles in the Greater Mekong Subregion (GMS), in alignment with UNESCO's cultural heritage preservation guidelines. The proposed database, curated with verified, high quality data, serves as a comprehensive knowledge base for educational and research purposes. The semantic search system demonstrated high effective-ness, showcasing its potential as a benchmark for cultural information retrieval. The study contributes to establishing similar systems in diverse domains, paving the way for ontology-driven approaches to support cultural heritage preservation and sus tainable web-based information search systems. The far-reaching implications offer valuable insights for the conservation and accessibility of cultural heritage.

Organizations are increasingly turning to chatbots to provide customer support via computer-generated, conversational, natural language answers to human queries. This paper describes a technique for creating an enterprise-specific chatbot (ESCB). We conducted an action research study to investigate the possibility of creating an ESCB with a local policy document knowledge base using readily available software tools, a basic level of programming competence, and user community feedback. The applied research on this chatbot leverages the power of Artificial Intelligence (AI), Natural Language Processing (NLP), and proprietary local data to transcend the typical limitations of conventional chatbots. Utilizing three quick-turn action research cycles, we evolved the chatbot to demonstrate high accuracy and relevance in its responses. The results indicate that our chatbot is becoming increasingly efficient in interpreting user queries, extracting necessary information, and formulating appropriate responses. The work underscores the significant potential of AI-powered chatbots for data interaction and the affordability of AI implementation, paving the way for organizations with limited resources to leverage the power of AI in their local operations. [ABSTRACT FROM AUTHOR]

Non-player Characters (NPCs) play a crucial role in shaping the player's experience and immersion in video games. However, despite advancements in technology and game design, NPCs continue to face several challenges that hinder their ability to provide engaging and realistic interactions. This has been true in some cases, such as open world games where the random NPCs do not have a lot of character depth or use repetitive sentences. This research aims to improve dialogue in video games by humanizing conversations between players and NPCs by using Google's Gemini API and Sentence-BERT framework. Gemini 1.0 Pro as a base model from Google to give natural responses and Sentence-BERT framework based on PyTorch and Transformers to compute sentence or text embeddings for more than 100 languages that can be compared with cosine similarity algorithm to find sentences with similar meanings. NPCs will be able to provide creative and unique quests to give to the players based on their conversations. This research provides insight on how LLMs such as Google's Gemini and Sentence BERT can be used in role-playing games to generate dynamic, unique conversations for NPCs without having to make the script manually [ABSTRACT FROM AUTHOR]

Legible language models, or LLMs, are poised to enable a broad range of new programming, feedback, scripting, and automated testing systems. However, recent accuracy and precision critiques highlight several near-term limitations of generative AI frameworks. To build a first-generation production version of retrieval-augmented generation systems that enhance information access through writing, we expected improvements to robustness, accuracy, and the overall performance of today's best LLMs, and rapid deployment of API integrations, interfaces, and workflows. As major data centers pushed hardware and infrastructure clouds started software scaling races, details of many ways to achieve improved near-term capabilities appeared, including ultra-large language models with probabilistic reasoning and factored representations, being introduced at this workshop. These emerging extensions form the basis for RAG system improvements. Ongoing research and development in other areas covers the hardware, software, and neural model design and training needs of programs, which will soon incorporate features into hybrid cloud production AI systems. [ABSTRACT FROM AUTHOR]

To enable machines to process state-of-practice Web API documentation, we propose a Transformer model for the generic task of identifying a Web API element within a syntax structure that matches a natural language query. We solve this semantic-search task with Transformer-based question answering and demonstrate the applicability of our approach to two different tasks, namely the discovery of endpoints and the identification of parameters in payload schemas. With samples from 2321 OpenAPI documentation, we prepare different datasets and fine-tune pre-trained BERT models to these two tasks. We evaluate the generalizability and the robustness of our fine-tuned models. We achieve accuracies of 81.95% for the parameter-matching and 88.44% for the endpoint-discovery task. [ABSTRACT FROM AUTHOR]

Countries are managed based on accurate and precise laws. Enacting appropriate and timely laws can cause national progress. Each law is a textual term that is added to the set of existing laws after passing a process with the approval of the assembly. In the review of each new law, the relevant laws are extracted and analyzed among the set of existing laws. This paper presents a new solution for extracting the relevant rules for a term from an existing set of rules using semantic similarity and deep learning techniques based on the BERT model. The proposed method encodes sentences or paragraphs of text in a fixed-length vector (dense vector space). Thereafter, the vectors are utilized to evaluate and score the semantic similarity of the sentences with the cosine distance measurement scale. In the proposed method, the machine can understand the meaning and concept of the sentences by using the BERT model coding method. The BERT model considers the position of the entities in the sentences. Then the semantic similarities of documents, calculating the degree of similarity between their documents with a subject, and detecting their semantic similarity are done. The results obtained from the test dataset indicated the precision and accuracy of the method in detecting semantic similarities of legal documents related to the Islamic Consultative Assembly of Iran, as well as the precision and accuracy of performance above 90%. [ABSTRACT FROM AUTHOR]

Objective: Various studies show that lexical or keyword search is not enough, because in this search the meaning of words and semantic relationships between keywords are ignored and semantic understanding is not achieved in this search. The purpose of this research is to investigate and measure the semantic search of users. Semantic search refers to a search that goes beyond the traditional search, i.e., the matching of the keywords of the search request with the keywords of the documents in the system and seeks to understand the meaning and semantic relationships between the keywords in the user's search request, which is used with the development and expansion of the semantic web and ontologies. The focus of this search is on obtaining a higher level of meaning from documents and inquiries and based on its content, which this high level meaning may be provided by ontologies. Semantic search expands the meaning and seeks machine understanding of the user's intent, query request and relationships between words and elevates the user's search strategy to a meaningful experience. In fact, semantic search describes the effort to produce accurate results by understanding the searcher's intent, texture and context of the query request, and the relationship between words. This search is of great interest to users and researchers due to its many advantages and applications. But besides the many advantages, it has over traditional and keyword search. It also has some problems and complications that elimination of these problems leads to the improvement and promotion of semantic search and helps users a lot.Methodology: The present study is quantitative in terms of approach and applied in terms of purpose, which has been done by survey method. The data collection tool was a researcher-made questionnaire. The statistical population of the study was 189 Iranian researchers who had published at least a research article on COVID-19, which Indexed in PubMed.Findings: Based on the research findings, from the perspective of Iranian researchers, the degree of recall and precision to semantic search in the PubMed is moderate (3). The amount of semantic gap in semantic search is relatively high (>3), the degree of accuracy and precision in retrieving results in semantic search is moderate (3), the degree of conceptual relevance in semantic search is moderate (3), the rate of retrieval of meaningful multi-word concepts in semantic search is moderate (3) and the rate of improvement and upgrade of overall performance in semantic search is relatively high (>3) in semantic searches at the database has been extensive.Conclusion: The results of the research in general showed that semantic search is a dynamic and challenging search that despite its various strengths and advantages for users in research, but still has its weaknesses and drawbacks that should be reviewed and revised by semantic search support experts such as ontology designers for the semantic search system. Understanding, identifying, and eliminating these weaknesses and problems, make semantic search to be a better way to respond to researchers for their research, as a result, researchers and users can achieve to richer results for compile their research work.

Objective: Various studies show that lexical or keyword search is not enough, because in this search the meaning of words and semantic relationships between keywords are ignored and semantic understanding is not achieved in this search. The purpose of this research is to investigate and measure the semantic search of users. Semantic search refers to a search that goes beyond the traditional search, i.e., the matching of the keywords of the search request with the keywords of the documents in the system and seeks to understand the meaning and semantic relationships between the keywords in the user's search request, which is used with the development and expansion of the semantic web and ontologies. The focus of this search is on obtaining a higher level of meaning from documents and inquiries and based on its content, which this high level meaning may be provided by ontologies. Semantic search expands the meaning and seeks machine understanding of the user's intent, query request and relationships between words and elevates the user's search strategy to a meaningful experience. In fact, semantic search describes the effort to produce accurate results by understanding the searcher's intent, texture and context of the query request, and the relationship between words. This search is of great interest to users and researchers due to its many advantages and applications. But besides the many advantages, it has over traditional and keyword search. It also has some problems and complications that elimination of these problems leads to the improvement and promotion of semantic search and helps users a lot. Methodology: The present study is quantitative in terms of approach and applied in terms of purpose, which has been done by survey method. The data collection tool was a researcher-made questionnaire. The statistical population of the study was 189 Iranian researchers who had published at least a research article on COVID-19, which Indexed in PubMed. Findings: Based on the research findings, from the perspective of Iranian researchers, the degree of recall and precision to semantic search in the PubMed is moderate (3). The amount of semantic gap in semantic search is relatively high (>3), the degree of accuracy and precision in retrieving results in semantic search is moderate (3), the degree of conceptual relevance in semantic search is moderate (3), the rate of retrieval of meaningful multi-word concepts in semantic search is moderate (3) and the rate of improvement and upgrade of overall performance in semantic search is relatively high (>3) in semantic searches at the database has been extensive. Conclusion: The results of the research in general showed that semantic search is a dynamic and challenging search that despite its various strengths and advantages for users in research, but still has its weaknesses and drawbacks that should be reviewed and revised by semantic search support experts such as ontology designers for the semantic search system. Understanding, identifying, and eliminating these weaknesses and problems, make semantic search to be a better way to respond to researchers for their research, as a result, researchers and users can achieve to richer results for compile their research work. [ABSTRACT FROM AUTHOR]

This paper presents the design and construction of GoKnowGraph, a Knowledge Graph (KG) that is customized exclusively for storing and semantically searching for system documents pertaining to the Government of Kerala (GoK). GoKnowGraph empowers the efficient retrieval of relevant government documents in multiple languages, thus augmenting accessibility and information retrieval within this GoK system. Our contributions encompass the development of a meticulously curated ontology, integrating essential information from GoK, and proposing a robust method for constructing and querying the KG. Moreover, our system supports cross-language document search for queries in English and advanced querying options, including attribute-based filters, to ensure precise information retrieval. Comparative assessments against a state-of-the-art system underscore GoKnowGraph's pronounced superiority in both relevance and accuracy. The meticulous alignment between user queries and the retrieved documents highlights the platform's capacity to effectively bridge the gap between unstructured data and the facilitation of informed decision-making within the GoK system. [ABSTRACT FROM AUTHOR]

Abstract Deep learning-based semantic search (DLSS) aims to bridge the gap between experts and non-experts in search. Experts can create precise queries due to their prior knowledge, while non-experts struggle with specific terms and concepts, making their queries less precise. Cloud infrastructure offers a practical and scalable platform for data owners to upload their data, making it accessible to intended data users. However, the contemporary single-owner/single-user (S/S) approach to DLSS schemes falls short of effectively leveraging the inherent multi-user capabilities of cloud infrastructure. Furthermore, most of these schemes delegate the dissemination of secret keys to a single trust point within the mutual distrust scenario in cloud infrastructure. This paper proposes a Secure Semantic Search using Deep Learning in a Blockchain-Assisted Multi-User Setting $$(S^3DBMS)$$ ( S 3 D B M S ) . Specifically, the seamless integration of attribute-based encryption with transfer learning allows the construction of DLSS in multi-owner/multi-user (M/M) settings. Further, blockchain’s smart contract mechanism allows a multi-attribute authority consensus-based generation of user private keys and system-wide global parameters in a mutual distrust M/M scenario. Finally, our scheme achieves privacy requirements and offers improved security and accuracy.

Recently, large pretrained language models (PLMs) have led a revolution in the information retrieval community. In most PLMs‐based retrieval frameworks, the ranking performance broadly depends on the model structure and the semantic complexity of the input text. Sequence‐to‐sequence generative models for question answering or text generation have proven to be competitive, so we wonder whether these models can improve ranking effectiveness by enhancing input semantics. This article introduces SE‐BERT, a semantically enhanced bidirectional encoder representation from transformers (BERT) based ranking framework that captures more semantic information by modifying the input text. SE‐BERT utilizes a pretrained generative language model to summarize both sides of the candidate passage and concatenate them into a new input sequence, allowing BERT to acquire more semantic information within the constraints of the input sequence's length. Experimental results from two Text Retrieval Conference datasets demonstrate that our approach's effectiveness increasing as the length of the input text increases. [ABSTRACT FROM AUTHOR]

The inclusion of collective intelligence through a semantic focused affective computing can incorporate intelligence to web search and ensure its compliance with the Web 3.0. In this article, a query growth model with inclusive and exclusive ontology semantics has been proposed for diversification of query recommendation in semantic search. The ontology semantics include query augmented ontology generation, agent‐driven attractor‐distractor generation to yield a merged ontology, and endowment of merged ontology by using hybridization of a series of knowledge bases. The strategy further includes the formulation of a semantic network and entity leveraging based on description logics (DLs) to improve the quality of query recommendation. A novel hierarchical entropy cognitive similarity covariance model has been proposed for yielding the most appropriate recommendable query words. The strategy also encompasses the user‐click information for capturing the current user intents to improve the quality queries recommended in semantic search, and thereby incorporate personalization. Experimentations are conducted for the CHiC dataset and the Spring 2006 Query Log dataset and an average accuracy of 96.27% and 92.01%, respectively, with a very low false discovery rate of 0.06 and 0.1 for the respective datasets. [ABSTRACT FROM AUTHOR]

Deep learning-based semantic search (DLSS) aims to bridge the gap between experts and non-experts in search. Experts can create precise queries due to their prior knowledge, while non-experts struggle with specific terms and concepts, making their queries less precise. Cloud infrastructure offers a practical and scalable platform for data owners to upload their data, making it accessible to intended data users. However, the contemporary single-owner/single-user (S/S) approach to DLSS schemes falls short of effectively leveraging the inherent multi-user capabilities of cloud infrastructure. Furthermore, most of these schemes delegate the dissemination of secret keys to a single trust point within the mutual distrust scenario in cloud infrastructure. This paper proposes a Secure Semantic Search using Deep Learning in a Blockchain-Assisted Multi-User Setting (S 3 D B M S) . Specifically, the seamless integration of attribute-based encryption with transfer learning allows the construction of DLSS in multi-owner/multi-user (M/M) settings. Further, blockchain's smart contract mechanism allows a multi-attribute authority consensus-based generation of user private keys and system-wide global parameters in a mutual distrust M/M scenario. Finally, our scheme achieves privacy requirements and offers improved security and accuracy. [ABSTRACT FROM AUTHOR]

In the current digital age, Artificial Intelligence, with an emphasis on large language models, has gained prominence in various fields such as finance and tax auditing, offering greater efficiency and accuracy in accessing information. This study proposes a software architecture for a mobile application as an intelligent personal assistant in this domain, integrating semantic search and large language models to optimize responses. The methodology included a literature review and a focus on emerging technologies through a technological surveillance study, culminating in an architecture inspired by the Voice Interaction Community Group of the W3C, adapted for non-intent based models with LLM. After developing the application, corporate data was integrated, facilitating semantic searches using a dense passage retrieval scheme and integrating it with language models. The results showed increased efficiency in obtaining financial and tax information and more contextual responses, speeding up data retrieval. This indicates that such integrations can revolutionize how professionals access information. However, it is essential to address ethical, security, and privacy aspects to ensure the reliability and sustained adoption of these tools. [ABSTRACT FROM AUTHOR]

In the evolving field of educational technology, knowledge mapping has emerged as a pivotal tool for university English education. This study examines its role in building a theoretical resource base to enhance the efficiency of organizing, accessing, and utilizing teaching materials. This research constructs a knowledge graph for English teaching resources by employing a seven-step process to create a domain ontology and an enhanced TF-IDF algorithm for keyword extraction. Results show the knowledge graph significantly boosts information retrieval accuracy and user satisfaction. The experimental group reported a 25% increase in learning efficiency, a 30% enhancement in the quality of learning outcomes, and a 12.63% rise in average grades, outperforming the control group. The findings suggest knowledge mapping substantially benefits the development of a theoretical resource base for university English teaching, improving teaching and learning quality.

This paper considers the problem of the generation of descriptors to reduce data volumes, text data resources, and search times through the use of the new factors of authorship, region, emotive meaning, and popularity, as well as a text category without special marks that can be used to generate descriptors. This approach allows the use of unique lexical-grammatical and distributive text regularities. The research outcomes can be used to determine authorship and text type. [ABSTRACT FROM AUTHOR]

The strong increase in scientific publications on SARS-CoV-2 infections and their long-term consequences requires efficient access to the literature. In a joint cooperation between ZB MED, Robert Koch Institute and the specialized information service for Pharmacy (PubPharm), search services were extended by suitable functionalities for an efficient search. In this project, the Narrative Service (PubPharm) was therefore extended by the so-called COVID-19 Overviews and Long COVID Overviews, which provide a structured overview of current research. For the semantic search engine preVIEW (ZB MED), a Long COVID filter was developed cooperatively, which allows a targeted search for preprints relevant to Long COVID. The resulting services are now freely available and in the public domain. In this article, the central challenges of monitoring literature on Long COVID are presented and it is described to what extent the newly developed functionalities support this monitoring.

Currently, cloud computing has become increasingly popular and thus, many people and institutions choose to put their data into the cloud instead of local environments. Given the massive amount of data and the fidelity of cloud servers, adequate security protection and efficient retrieval mechanisms for stored data have become critical problems. Attribute-based encryption brings the ability of fine-grained access control and can achieve a direct encrypted data search while being combined with searchable encryption algorithms. However, most existing schemes only support single-keyword or provide no ranking searching results, which could be inflexible and inefficient in satisfying the real world's actual needs. We propose a flexible multi-keyword ranked searchable attribute-based scheme using search trees to overcome the above-mentioned problems, allowing users to combine their fuzzy searching keywords with AND–OR logic gates. Moreover, our enhanced scheme not only improves its privacy protection but also goes a step further to apply a semantic search to boost the flexibility and the searching experience of users. With the proposed index-table method and the tree-based searching algorithm, we proved the efficiency and security of our schemes through a series of analyses and experiments. [ABSTRACT FROM AUTHOR]