Relevant Queries Research Articles

A Review of Hybrid Search Architectures: Integrating Keyword and Semantic Search to Optimize Query Relevance

Abstract—The advent of semantic search alongside the tra- ditional robustness of keyword search systems has established an intriguing dichotomy within the landscape of information retrieval. While keyword-based methods excel in terms of speci- ficity, semantic models offer contextual richness and intent aware- ness. However, each paradigm faces challenges in harnessing the strengths of the other. This paper investigates a hybrid search model that integrates both keyword and semantic search techniques, aiming to optimize relevance, interpretability, and user experience in complex information-seeking scenarios. We present an innovative hybrid architecture, conduct a comprehen- sive evaluation of its performance, and discuss its implications for information retrieval in specialized domains such as healthcare and education. Index Terms—Hybrid Search, Keyword Search, Semantic Search, Information Retrieval, Natural Language Processing, Search Architectures

Performance of chatbots in queries concerning fundamental concepts in photochemistry.

The advent of chatbots raises the possibility of a paradigm shift across society including the most technical of fields with regard to access to information, generation of knowledge, and dissemination of education and training. Photochemistry is a scientific endeavor with roots in chemistry and physics and branches that encompass diverse disciplines ranging from astronomy to zoology. Here, five chatbots have each been challenged with 13 photochemically relevant queries. The chatbots included ChatGPT 3.5, ChatGPT 4.0, Copilot, Gemini Advanced, and Meta AI. The queries encompassed fundamental concepts (e.g., "Why is the fluorescence spectrum typically the mirror image of the absorption spectrum?"), practical matters (e.g., "What is the inner filter effect and how to avoid it?"), philosophical matters ("Please create the most important photochemistry questions."), and specific molecular features (e.g., "Why are azo dyes non-fluorescent?"). The chatbots were moderately effective in answering queries concerning fundamental concepts in photochemistry but were glaringly deficient in specialized queries for dyes and fluorophores. In some instances, a correct response was embedded in verbose scientific nonsense whereas in others the entire response, while grammatically correct, was utterly meaningless. The unreliable accuracy makes present chatbots poorly suited for unaided educational purposes and highlights the importance of domain experts.

Learning to match patients to clinical trials using large language models

Objective:This study investigates the use of Large Language Models (LLMs) for matching patients to clinical trials (CTs) within an information retrieval pipeline. Our objective is to enhance the process of patient-trial matching by leveraging the semantic processing capabilities of LLMs, thereby improving the effectiveness of patient recruitment for clinical trials. Methods:We employed a multi-stage retrieval pipeline integrating various methodologies, including BM25 and Transformer-based rankers, along with LLM-based methods. Our primary datasets were the TREC Clinical Trials 2021–23 track collections. We compared LLM-based approaches, focusing on methods that leverage LLMs in query formulation, filtering, relevance ranking, and re-ranking of CTs. Results:Our results indicate that LLM-based systems, particularly those involving re-ranking with a fine-tuned LLM, outperform traditional methods in terms of nDCG and Precision measures. The study demonstrates that fine-tuning LLMs enhances their ability to find eligible trials. Moreover, our LLM-based approach is competitive with state-of-the-art systems in the TREC challenges.The study shows the effectiveness of LLMs in CT matching, highlighting their potential in handling complex semantic analysis and improving patient-trial matching. However, the use of LLMs increases the computational cost and reduces efficiency. We provide a detailed analysis of effectiveness-efficiency trade-offs. Conclusion:This research demonstrates the promising role of LLMs in enhancing the patient-to-clinical trial matching process, offering a significant advancement in the automation of patient recruitment. Future work should explore optimising the balance between computational cost and retrieval effectiveness in practical applications.

Boosting cross-modal retrieval in remote sensing via a novel unified attention network

With the rapid advent and abundance of remote sensing data in different modalities, cross-modal retrieval tasks have gained importance in the research community. Cross-modal retrieval belongs to the research paradigm in which the query is of one modality and the retrieved output is of the other modality. In this paper, the remote sensing (RS) data modalities considered are the earth observation optical data (aerial photos) and the corresponding hand-drawn sketches. The main challenge of the cross-modal retrieval research objective for optical remote sensing images and the corresponding sketches is the distribution gap between the shared embedding space of the modalities. Prior attempts to resolve this issue have not yielded satisfactory outcomes regarding accurately retrieving cross-modal sketch-image RS data. The state-of-the-art architectures used conventional convolutional architectures, which focused on local pixel-wise information about the modalities to be retrieved. This limits the interaction between the sketch texture and the corresponding image, making these models susceptible to overfitting datasets with particular scenarios. To circumvent this limitation, we suggest establishing multi-modal correspondence using a novel architecture of the combined self and cross-attention algorithms, SPCA-Net to minimize the modality gap by employing attention mechanisms for the query and other modalities. Efficient cross-modal retrieval is achieved through the suggested attention architecture, which empirically emphasizes the global information of the relevant query modality and bridges the domain gap through a unique pairwise cross-attention network. In addition to the novel architecture, this paper introduces a unique loss function, label-specific supervised contrastive loss, tailored to the intricacies of the task and to enhance the discriminative power of the learned embeddings. Extensive evaluations are conducted on two sketch-image remote sensing datasets, Earth-on-Canvas and RSketch. Under the same experimental conditions, the performance metrics of our proposed model beat the state-of-the-art architectures by significant margins of 16.7%, 18.9%, 33.7%, and 40.9% correspondingly.

Enhancing Biomedical Question Answering with Large Language Models

In the field of Information Retrieval, biomedical question answering is a specialized task that focuses on answering questions related to medical and healthcare domains. The goal is to provide accurate and relevant answers to the posed queries related to medical conditions, treatments, procedures, medications, and other healthcare-related topics. Well-designed models should efficiently retrieve relevant passages. Early retrieval models can quickly retrieve passages but often with low precision. In contrast, recently developed Large Language Models can retrieve documents with high precision but at a slower pace. To tackle this issue, we propose a two-stage retrieval approach that initially utilizes BM25 for a preliminary search to identify potential candidate documents; subsequently, a Large Language Model is fine-tuned to evaluate the relevance of query–document pairs. Experimental results indicate that our approach achieves comparative performances on the BioASQ and the TREC-COVID datasets.

Tractable Circuits in Database Theory

This work reviews how database theory uses tractable circuit classes from knowledge compilation. We present relevant query evaluation tasks, and notions of tractable circuits. We then show how these tractable circuits can be used to address database tasks. We first focus on Boolean provenance and its applications for aggregation tasks, in particular probabilistic query evaluation. We study these for Monadic Second Order (MSO) queries on trees, and for safe Conjunctive Queries (CQs) and Union of Conjunctive Queries (UCQs). We also study circuit representations of query answers, and their applications to enumeration tasks: both in the Boolean setting (for MSO) and the multivalued setting (for CQs and UCQs).

“It answers questions that I didn’t know I had”: PhD students’ evaluation of an information-sharing knowledge graph

PurposeInterdisciplinary PhD programs can be challenging as the vital information needed by students may not be readily available; it is scattered across the university’s websites, while tacit knowledge can be obtained only by interacting with people. Hence, there is a need to develop a knowledge management model to create, query and maintain a knowledge repository for interdisciplinary students. This study aims to propose a knowledge graph containing information on critical categories (faculty, classes, dissertations, etc.) and their relationships, extracted from multiple sources, essential for interdisciplinary PhD students. This study evaluates the usability of a participatory-designed knowledge graph intended to facilitate information exchange and decision-making.MethodologyThe authors used data from multiple sources (such as university websites, faculty profiles, publication and dissertation metadata and crowdsourced data) to generate a knowledge graph in the Neo4J Bloom platform. The authors recruited 15 interdisciplinary PhD students using convenience sampling from the University of Hawaiʻi at Mānoa at various PhD stages to design and populate the knowledge graph. Next, the authors conducted a mixed methods study to perform its usability evaluation. First, the authors engaged the students in a participatory design workshop to identify relevant graph queries. Second, the authors conducted semi-structured interviews to determine the usability of the knowledge graph and rate the queries. Each interview was coded with structural and thematic codes and was further analyzed using sentiment analysis in R programming language.FindingsThe usability findings demonstrate that interaction with this knowledge graph benefits PhD students by notably reducing uncertainty and academic stress, particularly among newcomers. Knowledge graph supported them in decision-making, especially when choosing collaborators (e.g. supervisor or dissertation committee members) in an interdisciplinary setting. Key helpful features are related to exploring student–faculty networks, milestones tracking, rapid access to aggregated data and insights into crowdsourced fellow students’ activities. However, they showed concerns about crowdsourced data privacy and accessibility. Although participants expressed the need for more qualitative data in the graph, they noted it helped identify people to talk to about the topics of their interest.OriginalityThe knowledge graph provides a solution to meet the personalized needs of doctoral researchers and has the potential to improve the information discovery and decision-making process substantially. It also includes the tacit knowledge exchange support missing from most current approaches, which is critical for this population and establishing interdisciplinary collaborations. This approach can be applied to other interdisciplinary programs and domains globally.

Google trends in infodemiology: Methodological steps to avoid irreproducible results and invalid conclusions

BackgroundGoogle Trends is a widely used tool for infodemiological surveys. However, irregularities in the random sampling and aggregation algorithms compromise the reliability of the relative search volume (RSV) and the regional online interest (ROI). ObjectiveThe study aims to unmask methodological criticalities commonly ignored in carrying out infodemiological surveys via Google Trends. A guide to avoiding these shortcomings is also provided. Material and methodsThe Google Topic “Coronavirus disease 2019” has been investigated using different timelapses, categories, and IP addresses. The same samples were manually collected multiple times to evaluate the RSV and ROI stability. Stability was estimated through indicators of variability (e.g., coefficient of percentage variation “CV%” and its 4-surprisal interval “4-I”). The content aggregation capacity of the algorithms relating to topics and categories was evaluated through the quantitative analysis of RSV and ROI and the qualitative examination of the related queries. ResultsThe stability of Google Trends’ RSV and ROI is not linked exclusively to the dataset dimension or the IP address. Subregional datasets can be highly unstable (e.g., CV% = 10, 4-I: [8,13]). Google Trends categories and topics can exclude relevant queries or include unnecessary queries. The statistical scenario is consistent with the following hypotheses: i) datasets containing too few queries are highly unstable, ii) the “interest over time” data format is generally reliable for evaluating trends and correlations, iii) Google Trends improvements have altered the RSV historical trends. ConclusionsGoogle Trends can be an effective and efficient infodemiological tool as long as the reliability of web search indexes is appropriately analyzed and weighted for the scientific goal. The methodological steps discussed in this study are critical to drawing valid and relevant scientific conclusions.

A modified Vector Space Model for semantic information retrieval

In this research, we present a modified Vector Space Model which focuses on the semantic relevance of words for retrieving documents. The modified VSM resolves the problem of the classical model performing only lexical matching of query terms to document terms for retrievals. This problem also restricts the classical model from retrieving documents that do not have exact match of query terms even if they are semantically relevant to the query. In the modified model, we introduced a Query Relevance Update technique, which pads the original query set with semantically relevant document terms for optimised semantic retrieval results. The modified model also includes a novel tf−p which replaces the tf−idf technique of the classical VSM, which is used to compute the Term Frequency weights. The replacement of the tf−idf resolves the problem of the classical model penalising terms that occur across documents with the assumption that they are stop words, which in practice, there are usually such words which carry relevant semantic information for documents’ retrieval. We also extended the cosine similarity function with a proportionality weight pqd, which moderates biases for high frequency of terms in longer documents. The pqd ensures that the frequency of query terms including the updated ones are accounted for in proportionality with documents size for the overall ranking of documents. The simulated results reveal that, the modified VSM does achieve semantic retrieval of documents beyond lexical matching of query and document terms.

Optimized continuous homecare provisioning through distributed data-driven semantic services and cross-organizational workflows

BackgroundIn healthcare, an increasing collaboration can be noticed between different caregivers, especially considering the shift to homecare. To provide optimal patient care, efficient coordination of data and workflows between these different stakeholders is required. To achieve this, data should be exposed in a machine-interpretable, reusable manner. In addition, there is a need for smart, dynamic, personalized and performant services provided on top of this data. Flexible workflows should be defined that realize their desired functionality, adhere to use case specific quality constraints and improve coordination across stakeholders. User interfaces should allow configuring all of this in an easy, user-friendly way.MethodsA distributed, generic, cascading reasoning reference architecture can solve the presented challenges. It can be instantiated with existing tools built upon Semantic Web technologies that provide data-driven semantic services and constructing cross-organizational workflows. These tools include RMLStreamer to generate Linked Data, DIVIDE to adaptively manage contextually relevant local queries, Streaming MASSIF to deploy reusable services, AMADEUS to compose semantic workflows, and RMLEditor and Matey to configure rules to generate Linked Data.ResultsA use case demonstrator is built on a scenario that focuses on personalized smart monitoring and cross-organizational treatment planning. The performance and usability of the demonstrator’s implementation is evaluated. The former shows that the monitoring pipeline efficiently processes a stream of 14 observations per second: RMLStreamer maps JSON observations to RDF in 13.5 ms, a C-SPARQL query to generate fever alarms is executed on a window of 5 s in 26.4 ms, and Streaming MASSIF generates a smart notification for fever alarms based on severity and urgency in 1539.5 ms. DIVIDE derives the C-SPARQL queries in 7249.5 ms, while AMADEUS constructs a colon cancer treatment plan and performs conflict detection with it in 190.8 ms and 1335.7 ms, respectively.ConclusionsExisting tools built upon Semantic Web technologies can be leveraged to optimize continuous care provisioning. The evaluation of the building blocks on a realistic homecare monitoring use case demonstrates their applicability, usability and good performance. Further extending the available user interfaces for some tools is required to increase their adoption.

Clinical features of auto-aggressive behavior in borderline personality disorder: a review of current research

Borderline personality disorder (BPD) is a common psychiatric disorder characterized by severe auto-aggression (AA) in the form of suicide attempts (SA) and non-suicidal self-injury (NSSI). The purpose of this review was to describe the current knowledge about the clinical features of self-harming behavior in borderline personality disorder. Materials and methods: The eLibrary, PubMed, CNKI, and Google Scholar databases were searched for articles on the relevant search query for the last 11 years. As a result, 28 articles were selected and summarized (a total of 7,284 BPD patients and 134 controls were included). Results: Suicidal attempts occur in 75 % of BPD patients, and NSSIs — in 90 %. AA behavior varies with age: adolescents tend to NSSIs, while adults more often undertake SAs. Depending on the type of clinical dynamics, AA in BPD may be impulsive, demonstrative, associated with comorbid addiction, or occur in the context of depersonalization. Among BPD symptoms, feelings of chronic emptiness, avoidance of abandonment, emotional instability, and identity disturbance are most commonly associated with auto-aggression. Risk factors for self-harming behavior in BPD include traumatic childhood events, especially physical and sexual abuse, and stress caused by microsocial conflict. Men with BPD and AA more often have comorbid narcissistic, antisocial, paranoid, and schizotypal personality disorders, as well as substance use disorders. Women with borderline personality disorder and AA tend to suffer more from addictive and obsessive-compulsive personality disorders, as well as eating disorders, particularly bulimia nervosa. In conclusion, self-harming behavior in BPD has many clinical features and can manifest in different forms. It is always necessary to study the predominant clinical manifestations, risk factors, and comorbid disorders to be able to assess the severity of AA.

What drives the real estate market? Could behavioral indicators be useful in house pricing models?

PurposeThe objective of this paper is to examine the determinants of the Greek house market during the period 2006–2022 using not only economic variables but also behavioral variables, taking advantage of available information on the volume of Google searches. In order to quantify the behavioral variables, we implement a Python code using the Pytrends 4.9.2 library.Design/methodology/approachIn our study, we assert that models relying solely on economic variables, such as GDP growth, mortgage interest rates and inflation, may lack precision compared to those that integrate behavioral indicators. Recognizing the importance of behavioral insights, we incorporate Google Trends data as a key behavioral indicator, aiming to enhance our understanding of market dynamics by capturing online interest in Greek real estate through searches related to house prices, sales and related topics. To quantify our behavioral indicators, we utilize a Python code leveraging Pytrends, enabling us to extract relevant queries for global and local searches. We employ the EGARCH(1,1) model on the Greek house price index, testing several macroeconomic variables alongside our Google Trends indexes to explain housing returns.FindingsOur findings show that in some cases the relationship between economic variables, such as inflation and mortgage rates, and house prices is not always consistent with the theory because we should highlight the special conditions of the examined country. The country of our sample, Greece, presents the special case of a country with severe sovereign debt issues, which at the same time has the privilege to have a strong currency and the support and the obligations of being an EU/EMU member.Practical implicationsThe results suggest that Google Trends can be a valuable tool for academics and practitioners in order to understand what drives house prices. However, further research should be carried out on this topic, for example, causality relationships, to gain deeper insight into the possibilities and limitations of using such tools in analyzing housing market trends.Originality/valueThis is the first paper, to the best of our knowledge, that examines the benefits of Google Trends in studying the Greek house market.

NowIKnowMyABCD: A global resource hub for researchers using data from the ABCD Study

The Adolescent Brain and Cognitive Development (ABCD) Study, involving over 11,000 youth and their families, is a groundbreaking project examining various factors impacting brain and cognitive development. Despite yielding hundreds of publications and counting, the ABCD Study has lacked a centralized help platform to assist researchers in navigating and analyzing the extensive ABCD dataset. To support the ABCD research community, we created NowIKnowMyABCD, the first centralized documentation and communication resource publicly available to researchers using ABCD Study data. It consists of two core elements: a user-focused website and a moderated discussion board. The website serves as a repository for ABCD-related resources, tutorials, and a live feed of relevant updates and queries sourced from social media websites. The discussion board offers a platform for researchers to seek guidance, troubleshoot issues, and engage with peers. Our aim is for NowIKnowMyABCD to grow with participation from the ABCD research community, fostering transparency, collaboration, and adherence to open science principles.

Robustness Verification of Multi-Class Tree Ensembles

Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, which are slightly perturbed examples that elicit a misprediction. There has been significant research on designing approaches to verify the robustness of tree ensembles to such attacks. However, existing verification algorithms for tree ensembles are only able to analyze binary classifiers and hence address multiclass problems by reducing them to binary ones using a one-versus-other strategy. In this paper, we show that naively applying this strategy can yield incorrect results in certain situations. We address this shortcoming by proposing a novel approximate heuristic approach to verification for multiclass tree ensembles. Our approach is based on a novel generalization of the verification task, which we show emits other relevant verification queries.

Multi-Modal Deep Learning based Metadata Extensions for Video Clipping

General video search and recommendation systems primarily rely on metadata and personal information. Metadata includes file names, keywords, tags, and genres, among others, and is used to describe the video's content. The video platform assesses the relevance of user search queries to the video metadata and presents search results in order of highest relevance. Recommendations are based on videos with metadata judged to be similar to the one the user is currently watching. Most platforms offer search and recommendation services by employing separate algorithms for metadata and personal information. Therefore, metadata plays a vital role in video search. Video service platforms develop various algorithms to provide users with more accurate search results and recommendations. Quantifying video similarity is essential to enhance the accuracy of search results and recommendations. Since content producers primarily provide basic metadata, it can be abused. Additionally, the resemblance between similar video segments may diminish depending on its duration. This paper proposes a metadata expansion model that utilizes object recognition and Speech-to-Text (STT) technology. The model selects key objects by analyzing the frequency of their appearance in the video, extracts audio separately, transcribes it into text, and extracts the script. Scripts are quantified by tokenizing them into words using text-mining techniques. By augmenting metadata with key objects and script tokens, various video content search and recommendation platforms are expected to deliver results closer to user search terms and recommend related content.

Research on the Application of BiLSTM-CRF Model in the Field of Chinese Modern History Question-and-Answer

Knowledge graph is the key technology of knowledge engineering in the era of big data. Using the powerful semantic understanding and knowledge organization ability of knowledge graph, it can be a better solution to the problems such as the disordered and over-wide coverage of knowledge related to modern Chinese history. The core of this paper is to use high-quality machine learning and deep learning algorithms with the support of big data knowledge graph to obtain the problem analysis result through natural language processing, and then match the problem analysis result with the question template to generate relevant query statements in the constructed knowledge graph to query relevant content through the knowledge graph rich semantic relations. The close relationship between the entities returns the most appropriate information for the user. The experimental results show that the designed question-and-answer system of modern Chinese history fills the gap in this field to a certain extent.

ОСОБЛИВОСТІ ТЕХНОЛОГІЇ ПОШУКОВОЇ ОПТИМІЗАЦІЇ ЯК ОДНІЄЇ З ОСНОВНИХ СКЛАДОВИХ ІНСТРУМЕНТУ ЦИФРОВОГО МАРКЕТИНГУ

The rapid development of information technology, based on the principles of technological convergence, has led to the fact that sales through websites and online business have recently become particularly popular. You can attract the target audience to your website by using search engine optimization. Search engine optimization is the comprehensive development and promotion of a company's website to ensure that it reaches the top positions as a result of search engine results for selected queries, with the aim of increasing traffic and further generating income. The paper examines the technology of search engine optimization as one of the elements of digital marketing aimed at increasing the volume of online sales and improving the customer experience in using a company's website. It is substantiated that the higher the position of the site, the more users go to it. It is found that the following tasks are important for the results of website promotion: increasing the relevance of pages to search queries (relevance); optimization of structure and content; improvement of commercial factors; increasing external factors of resource significance. The paper notes that search engine optimization technology has great prospects for further use in business, as well as high efficiency in promoting goods or services and increasing sales through websites. The paper also considers a component that is part of the digital marketing system – search engine optimization SEO. SEO is the comprehensive strategy for developing and promoting a company's website to secure top positions in search engine results pages (SERPs) for relevant user queries. This strategic approach aims to dramatically increase website traffic, ultimately leading to enhanced sales and revenue generation. The process of creating a website optimization algorithm, which includes the necessary steps for internal and external optimization, is formulated, and a comparison of some Internet marketing tools is made. The paper also considers some theoretical issues of changing marketing technologies for interaction with customers in the digital environment.

Potential application of ChatGPT in Helicobacter pylori disease relevant queries.

Advances in artificial intelligence are gradually transforming various fields, but its applicability among ordinary people is unknown. This study aims to explore the ability of a large language model to address Helicobacter pylori related questions. We created several prompts on the basis of guidelines and the clinical concerns of patients. The capacity of ChatGPT on Helicobacter pylori queries was evaluated by experts. Ordinary people assessed the applicability. The responses to each prompt in ChatGPT-4 were good in terms of response length and repeatability. There was good agreement in each dimension (Fleiss' kappa ranged from 0.302 to 0.690, p < 0.05). The accuracy, completeness, usefulness, comprehension and satisfaction scores of the experts were generally high. Rated usefulness and comprehension among ordinary people were significantly lower than expert, while medical students gave a relatively positive evaluation. ChatGPT-4 performs well in resolving Helicobacter pylori related questions. Large language models may become an excellent tool for medical students in the future, but still requires further research and validation.

Features of software implementing the prefix search method in cryptographically protected databases

The article addresses the specific considerations associated with the development of software implementing the prefix search method in cryptographically protected databases. This method is a variant of symmetric searchable encryption, which allows search among the encrypted data. The prefix search method allows searching for prefixes among encrypted data without the need for decryption. Such an approach resolves the issue of maintaining data confidentiality stored on remote or cloud servers. However, its usage introduces a set of issues that must be considered during the development of the corresponding software. The paper analyzes the requirements for software that implements the prefix search method, defines the software architecture, and justifies the choice of technologies and tools for software implementation, including ASP.NET, Java, JavaScript, PHP, Python programming languages, MongoDB database management system, and the FastAPI framework. A description of the deployment process of the corresponding software is provided. To assess the performance of the developed software, the well-known Apache JMeter tool for conducting load testing was utilized. The obtained performance evaluations of the proposed solution indicate acceptable time delays in processing relevant data search queries.

STES Chatbot Using Flutter: STES Dialogic AI

STES Dialogic AI is a pioneering college-related chatbot designed to streamline the information and inquiry process for students interested in the Sinhgad Technical Education Society (STES). This innovative virtual assistant offers a userfriendly platform for students to access vital information about STES, such as admission procedures, course details, campus facilities, and other relevant queries. By harnessing natural language processing(NLP) and artificial intelligence, this chatbot serves as a responsive, round-the-clock information resource, ensuring that students can obtain answers to their questions promptly and efficiently. STES Dialogic AI not only enhances the student experience but also showcases STES's commitment to technological advancements and student-centric services