Query Construction Research Articles

CPEQA: A Large Language Model Based Knowledge Base Retrieval System for Chinese Confidentiality Knowledge Question Answering

Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, particularly in the construction of the intelligent question-answering system. These systems, especially in specialized fields, usually rely on NLP through the retrieval of corpus and answering databases to efficiently provide accurate and concise answers. This paper focuses on the national confidentiality publicity and education field, aiming to address the dilemma of inaccurate knowledge retrieval in this field. Therefore, we design an intelligent confidentiality question-answering system CPEQA by comprehensively utilizing the LLMs platform and information retrieval technique. CPEQA is capable of providing professional answers to questions about Chinese confidentiality publicity and education raised by users. Additionally, we also integrate the conventional database retrieval technique and LLMs into the database query construction, enabling CPEQA to perform real-time queries and data analysis for both single-table and multi-table querying tasks. Through extensive experiments with generated query sentences, we show both methodological comparisons and empirical evaluations of CPEQA’s performance. Experimental results indicate that CPEQA has achieved competitive results on answering precision, recall rate and other metrics. Finally, we explore the challenges of the CPEQA system associated with these techniques and outline potential avenues for future research in this emerging field.

HERALD: A domain-specific query language for longitudinal health data analytics

BackgroundLarge-scale health data has significant potential for research and innovation, especially with longitudinal data offering insights into prevention, disease progression, and treatment effects. Yet, analyzing this data type is complex, as data points are repeatedly documented along the timeline. As a consequence, extracting cross-sectional tabular data suitable for statistical analysis and machine learning can be challenging for medical researchers and data scientists alike, with existing tools lacking balance between ease-of-use and comprehensiveness. ObjectiveThis paper introduces HERALD, a novel domain-specific query language designed to support the transformation of longitudinal health data into cross-sectional tables. We describe the basic concepts, the query syntax, a graphical user interface for constructing and executing HERALD queries, as well as an integration into Informatics for Integrating Biology and the Bedside (i2b2). MethodsThe syntax of HERALD mimics natural language and supports different query types for selection, aggregation, analysis of relationships, and searching for data points based on filter expressions and temporal constraints. Using a hierarchical concept model, queries are executed individually for the data of each patient, while constructing tabular output. HERALD is closed, meaning that queries process data points and generate data points. Queries can refer to data points that have been produced by previous queries, providing a simple, but powerful nesting mechanism. ResultsThe open-source implementation consists of a HERALD query parser, an execution engine, as well as a web-based user interface for query construction and statistical analysis. The implementation can be deployed as a standalone component and integrated into self-service data analytics environments like i2b2 as a plugin. HERALD can be valuable tool for data scientists and machine learning experts, as it simplifies the process of transforming longitudinal health data into tables and data matrices. ConclusionThe construction of cross-sectional tables from longitudinal data can be supported through dedicated query languages that strike a reasonable balance between language complexity and transformation capabilities.

VQFT: A Visual Query Approach Based on Full-Text Search for Knowledge Graphs

Existing knowledge graph query approaches, whether traditional textual query languages or visual query languages, have steep learning curves that are unfriendly for non-expert users. This demonstration presents a Visual Query approach based on Full-Text search for knowledge graphs, called VQFT, which simplifies the process of querying knowledge graphs for users. Inspired by full-text search techniques, VQFT aims to combine the user-friendliness of visual query with the intuitiveness of full-text search , enabling users to query knowledge graphs as straightforward as using a search engine. Faceted full-text indexes, visual query constructor , and an interactive user interface are designed to achieve this goal. User tests and surveys have demonstrated that VQFT is more user-friendly and easier to learn than existing methods, which simplifies the construction of knowledge graph queries for non-expert users.

IRBEVF-Q: Optimization of Image-Radar Fusion Algorithm Based on Bird's Eye View Features.

In autonomous driving, the fusion of multiple sensors is considered essential to improve the accuracy and safety of 3D object detection. Currently, a fusion scheme combining low-cost cameras with highly robust radars can counteract the performance degradation caused by harsh environments. In this paper, we propose the IRBEVF-Q model, which mainly consists of BEV (Bird's Eye View) fusion coding module and an object decoder module.The BEV fusion coding module solves the problem of unified representation of different modal information by fusing the image and radar features through 3D spatial reference points as a medium. The query in the object decoder, as a core component, plays an important role in detection. In this paper, Heat Map-Guided Query Initialization (HGQI) and Dynamic Position Encoding (DPE) are proposed in query construction to increase the a priori information of the query. The Auxiliary Noise Query (ANQ) then helps to stabilize the matching. The experimental results demonstrate that the proposed fusion model IRBEVF-Q achieves an NDS of 0.575 and a mAP of 0.476 on the nuScenes test set. Compared to recent state-of-the-art methods, our model shows significant advantages, thus indicating that our approach contributes to improving detection accuracy.

Examining Implications of Search Query Construction on Sentiment Analysis: The Case of Brandwatch

Consistent with other fields, advertising research is currently facing a replication crisis, evoking methodological concerns regarding the reproducibility of research findings. To address this crisis, we systematically reviewed seven computational advertising studies that collected and analyzed the sentiment of tweets. Upon identifying five studies that reported replicable data collection processes, we utilized the original search queries to recollect tweets using a third-party platform, Brandwatch. We also replicated data collection using iterative complex Boolean (ICB) operators, which sought to enhance the resulting dataset precision. Then, we juxtaposed the effects of search query design (original vs. ICB) using sentiment analysis. Together, the findings suggest that how a query is written can affect measures of precision, engagement, sentiment, and recall. Tests of precision are recommended to mitigate the effects of variance in retrieval relevance.

Entity and Relation Linking for Knowledge Graph Question Answering Using Gradual Searching

Knowledge graph question answering (KGQA) systems have an important role in retrieving data from a knowledge graph (KG). With the system, regular users can access data from a KG without the need to construct a formal SPARQL query. KGQA systems receive a natural language question (NLQ) and translate it into a SPARQL query through three main tasks, namely, entity and relation detection, entity and relation linking, and query construction. However, the translation is not trivial due to lexical gaps and entity ambiguity that may occur during entity or relation linking. This research proposed an approach based on multiclass classification of NLQ whose entity occurrences are detected into categories based on KG relations to address the lexical gap challenge. Next, to solve the entity ambiguity challenge, this research proposed a three-stage searching procedure to determine appropriate KG entities associated with the NLQ entities, given the correspondence between the NLQ and a particular KG relation. This three-stage searching consisted of text-based searching, vector-based searching, and entity and relation pairing. The proposed approach was evaluated on the SimpleQuestions and LC-QuAD 2.0 datasets. The experiments demonstrated that the proposed approach outperformed the state-of-the-art baseline. For the relation linking task, the proposed approach reached 89.87% and 74.83% recall for the SimpleQuestions and LC-QuAD 2.0, respectively. This approach also achieved 91.74% and 61.96% recall on the entity linking tasks for the SimpleQuestions and LC-QuAD 2.0, respectively.

False Positives and Deceptive Errors in SQL Assessment: A Large-Scale Analysis of Online Judge Systems

Online Judge Systems (OJSs) play a crucial role in evaluating SQL programming skills. However, OJSs may not accurately evaluate students’ queries as the error-detection capabilities of test sets are insufficient, resulting in false positives that can mislead students and hinder their learning. This study analyzes a large-scale OJS’s evaluation dataset and identifies more than 110,000 (1.94%) false-positive queries. It also validates existing SQL error categorization and reveals a new type of logical error called deceptive error, which occurs when students construct queries that pass specific test cases but fail to solve the actual problem. This type of error has been overlooked in previous research and can provide new insights into how to improve OJSs by enhancing test cases and feedback. This study contributes to the understanding of assessment and evaluation practices and processes in programming education, particularly the contribution that OJSs make to student learning and to course, staff, and institutional development. It also suggests error prevention and detection techniques that can improve the effectiveness and fairness of OJSs in programming education and competitions.

HiRegEx: Interactive Visual Query and Exploration of Multivariate Hierarchical Data.

When using exploratory visual analysis to examine multivariate hierarchical data, users often need to query data to narrow down the scope of analysis. However, formulating effective query expressions remains a challenge for multivariate hierarchical data, particularly when datasets become very large. To address this issue, we develop a declarative grammar, HiRegEx (Hierarchical data Regular Expression), for querying and exploring multivariate hierarchical data. Rooted in the extended multi-level task topology framework for tree visualizations (e-MLTT), HiRegEx delineates three query targets (node, path, and subtree) and two aspects for querying these targets (features and positions), and uses operators developed based on classical regular expressions for query construction. Based on the HiRegEx grammar, we develop an exploratory framework for querying and exploring multivariate hierarchical data and integrate it into the TreeQueryER prototype system. The exploratory framework includes three major components: top-down pattern specification, bottom-up data-driven inquiry, and context-creation data overview. We validate the expressiveness of HiRegEx with the tasks from the e-MLTT framework and showcase the utility and effectiveness of TreeQueryER system through a case study involving expert users in the analysis of a citation tree dataset.

ChatReview: A ChatGPT-enabled natural language processing framework to study domain-specific user reviews

Intelligent search engines including pre-trained generative transformers (GPT) have revolutionized the user search experience. Several fields including e-commerce, education, and hospitality are increasingly exploring GPT tools to study user reviews and gain critical insights to improve their service quality. However, massive user-review data and imprecise prompt engineering lead to biased, irrelevant, and impersonal search results. In addition, exposing user data to these search engines may pose privacy issues. Motivated by these factors, we present ChatReview, a ChatGPT-enabled natural language processing (NLP) framework that effectively studies domain-specific user reviews to offer relevant and personalized search results at multiple levels of granularity. The framework accomplishes this task using four phases including data collection, tokenization, query construction, and response generation. The data collection phase involves gathering domain-specific user reviews from public and private repositories. In the tokenization phase, ChatReview applies sentiment analysis to extract keywords and categorize them into various sentiment classes. This process creates a token repository that best describes the user sentiments for a given user-review data. In the query construction phase, the framework uses the token repository and domain knowledge to construct three types of ChatGPT prompts including explicit, implicit, and creative. In the response generation phase, ChatReview pipelines these prompts into ChatGPT to generate search results at varying levels of granularity. We analyze our framework using three real-world domains including education, local restaurants, and hospitality. We assert that our framework simplifies prompt engineering for general users to produce effective results while minimizing the exposure of sensitive user data to search engines. We also present a one-of-a-kind Large Language Model (LLM) peer assessment of the ChatReview framework. Specifically, we employ Google’s Bard to objectively and qualitatively analyze the various ChatReview outputs. Our Bard-based analyses yield over 90% satisfaction, establishing ChatReview as a viable survey analysis tool.

A study of NoSQL query injection in Neo4j

Query injection refers to a class of attack types that involve the insertion of maliciously crafted query parameters in database query operations, and/or API calls. Although these security issues have been studied extensively in relational databases, the possibility and incidence of injection in NoSQL data stores –which are built around fundamentally different data models– has received less attention.In this article, we present the outcomes of an in-depth investigation of the injection-related risks in the Neo4j graph database and its broader ecosystem. This study is based on (i) an investigation of the distributed execution of parameterized queries, from language-specific client connectors, to communication (Bolt protocol) and execution in Neo4j (in query plans), and (ii) identifying residual injection problems in cases where parameterized, static queries will not suffice. The study involves code-centric data flow investigation of the Neo4j code base, and is complemented with a test suite of injection test cases.We found that (i) the mechanism of query parameterization as promoted by Neo4j is effective in mitigating traditional query injection threats, and (ii) traditional query injection attacks however remain possible when this approach is not adopted, which is realistic for applications that necessarily involve dynamic, run-time query construction (e.g., analytics pipelines).

Finding environmental discourse in historical newspapers: a topic model workflow for query disambiguation


 
 
 Digitized historical newspapers are a treasure trove of information for our understanding of the past. As one popular application, the frequencies of query matches can be used to understand the prevalence of some discourse in a historical era. This requires the construction good queries: broad enough to capture diverse contexts and narrow enough to exclude irrelevant ones. For historical research in digital humanities, targeted queries that emphasize precision have been advised. In this paper, we develop an alternative approach, by using broad queries to cast a wider net and then using topic models built on the match contexts to filter out irrelevant matches. Specifically, we look for contexts discussing environmental issues throughout the 20th century using a corpus of two Australian newspapers. We report on a comparison of iteratively constructed narrow and broad queries and their precision and recall, and find our approach to discover roughly 7-10x more matches with a comparable level of accuracy. This combined approach can work well for focussed research projects where deliberate query construction and qualitative feedback on the results is feasible.
 
 

Systematic Literature Review on Ontology-based Indonesian Question Answering System

Question-Answering (QA) systems at the intersection of natural language processing, information retrieval, and knowledge representation aim to provide efficient responses to natural language queries. These systems have seen extensive development in English and languages like Indonesian present unique challenges and opportunities. This literature review paper delves into the state of ontology-based Indonesian QA systems, highlighting critical challenges. The first challenge lies in sentence understanding, variations, and complexity. Most systems rely on syntactic analysis and struggle to grasp sentence semantics. Complex sentences, especially in Indonesian, pose difficulties in parsing, semantic interpretation, and knowledge extraction. Addressing these linguistic intricacies is pivotal for accurate responses. Secondly, template-based SPARQL query construction, commonly used in Indonesian QA systems, suffers from semantic gaps and inflexibility. Advanced techniques like semantic matching algorithms and dynamic template generation can bridge these gaps and adapt to evolving ontologies. Thirdly, lexical gaps and ambiguity hinder QA systems. Bridging vocabulary mismatches between user queries and ontology labels remains a challenge. Strategies like synonym expansion, word embedding, and ontology enrichment must be explored further to overcome these challenges. Lastly, the review discusses the potential of developing multi-domain ontologies to broaden the knowledge coverage of QA systems. While this presents complex linguistic and ontological challenges, it offers the advantage of responding to various user queries across various domains. This literature review identifies crucial challenges in developing ontology-based Indonesian QA systems and suggests innovative approaches to address these challenges.

Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis

There have been many decades of work on optimizing query processing in database management systems. Recently, modern machine learning (ML), and specifically reinforcement learning (RL), has gained increased attention as a means to develop a query optimizer (QO). In this work, we take a closer look at two recent state-of-the-art (SOTA) RL-based QO methods to better understand their behavior. We find that these RL-based methods do not generalize as well as it seems at first glance. Thus, we ask a simple question: How do SOTA RL-based QOs compare to a simple, modern, adaptive query processing approach? To answer this question, we choose two simple adaptive query processing techniques and implemented them in PostgreSQL. The first adapts an individual join operation on-the-fly and switches between a Nested Loop Join algorithm and a Hash Join algorithm to avoid sub-optimal join algorithm decisions. The second is a technique called Lookahead Information Passing (LIP), in which adaptive semijoin techniques are used to make a pipeline of join operations execute efficiently. To our surprise, we find that this simple adaptive query processing approach is not only competitive to the SOTA RL-based approaches but, in some cases, outperforms the RL-based approaches. The adaptive approach is also appealing because it does not require an expensive training step, and it is fully interpretable compared to the RL-based QO approaches. Further, the adaptive method works across complex query constructs that RL-based QO methods currently cannot optimize.

Optimizing Keyword Search Over Federated RDF Systems

The issue of keyword search in federated resource description framework(RDF) systems is revisited in this paper. Numerous independent SPARQL endpoints that solely offer SPARQL query interfaces make up a federated RDF system. Others find it challenging to remotely build up the global inverted indices over the full RDF network by downloading the dataset at various SPARQL endpoints. This poses a challenge for existing keyword search approaches. In this paper, we propose a keyword search approach for federated RDF systems without building up global inverted indices on the entire RDF graph. We build an offline schema graph for the federated RDF system. During query evaluation, the full-text search interfaces provided by existing SPARQL endpoints were used to map keywords to vertices in the schema graph. Subsequently, the schema graph was explored to construct SPARQL queries from the keywords. The constructed queries were evaluated over the underlying federated RDF systems. Some cost models were proposed to measure keyword mapping and query construction. On the other hand, to further improve the efficiency, a multiple query optimization strategy was designed to rewrite the queries and share the common computation during evaluation. Extensive experiments on real RDF datasets show that the proposed techniques are effective.

On the design of linked datasets mapping networks of collaboration in the genomic sequencing of Saccharomyces cerevisiae, Homo sapiens, and Sus scrofa.

This data note describes a unique two-step methodology to construct six linked datasets covering the sequencing of Saccharomyces cerevisiae, Homo sapiens, and Sus scrofa genomes. The datasets were used as evidence in a project that investigated the history of genomic science. To design the datasets, we first retrieved all sequence submission data from the European Nucleotide Archive (ENA), including accession numbers associated with each of our three species. Second, we used these accession numbers to construct queries to retrieve peer-reviewed scientific publications that first described these sequence submissions in the scientific literature. For each species, this resulted in two associated datasets: 1) A .csv file documenting the PMID of each article describing new sequences, all paper authors, all institutional affiliations of each author, countries of institution, year of first submission to the ENA (when available), and the year of article publication, and 2) A .csv file documenting all institutions submitting to the ENA, number of nucleotides sequenced and years of submission to the database. We utilised these datasets to understand how institutional collaboration shaped sequencing efforts, and to systematically identify important institutions and changes in the structure of research communities throughout the history of genomics and across our three target species. This data note, therefore, should aid researchers who would like to use these data for future analyses by making the methodology that underpins it transparent. Further, by detailing our methodology, researchers may be able to utilise our approach to construct similar datasets in the future.

Students' Use of the Artificial Intelligence Language Model in their Learning Process

Generative Artificial Intelligence (GAI), of which ChatGPT is an exemplary tool, is beginning to revolutionize the way people search for information and use the information they acquire in their personal and professional lives. ChatGPT is showing a strong track record in a variety of tasks, such as generating text, summarizing text and answering questions during a conversation. It has the potential to revolutionize a wide range of fields - including education. The purpose of this article is to evaluate the extent to which the ChatGPT language model can be applied in the learning process for two types of students: full-time and part-time. Additionally, this article assesses the level of students' familiarity with intelligent chat functionality and their ability to construct queries directed to it. The study found that the use of an advanced language model based on artificial intelligence is more beneficial for full-time students in the learning process. However, there was no statistically significant difference in the knowledge of intelligent chat functionality and the ability to construct queries directed to it between full-time and part-time students.

Towards semantic-driven boolean query formalization for biomedical systematic literature reviews

ObjectiveStudy identification refers to formalizing an effective search over biomedical databases for retrieving all eligible evidence for a systematic review. Manual construction of queries, where a user submit a search query for which a biomedical search system such as PubMed would identify the most relevant documents, has been recognized as a very costly step in conducting systematic reviews. The objective of this paper is to present an automatic query generation approach to reduce the time and labor cost of manual biomedical study identification. Materials and MethodsThe evaluation benchmark is the widely adopted CLEF 2018 Technology Assisted Reviews (TAR) collection, with 72 systematic reviews on Diagnosis Test Accuracy. We use and fine-tune pre-trained language models for generating high-level key-phrases and their dense embeddings. We constructed and published a dataset consists of almost one million PubMed articles’ abstracts and their keywords for fine-tuning pre-trained language models. We also use concepts that are represented in the Unified Medical Language System, UMLS, for query expansion and embedding generation. We exploit and test different clustering methods, namely Agglomerative clustering, Affinity Propagation, and K-Means, over the generated embeddings to form query clauses. ResultsOur proposed methods outperform existing state-of-the-art automatic query generation models across Precision (0.0821 compared with 0.005), Recall (0.9676 compared with 0.878), and F-measures (0.2898 compared with 0.0356 in F3 measure). In addition, some of the proposed methods can even outperform the performance of the manually crafted queries in some specific measures. ConclusionThe proposed model in this paper can be utilized to form an effective initial search query that can be further refined and updated by human reviewers for achieving the desired performance. For future work, we would like to explore the application of the presented query formalization methods in existing study identification methodologies and techniques, especially those that iteratively train machine learning models based on the domain experts’ feedback on the relevancy of the retrieved studies.

Discerning appropriate reviews based on hierarchical deep neural network for answering product-related queries

In recent years, E-Commerce is globally increasing among online purchaser, in which customer post product related queries for finding the best product in online shopping. Manually answering the product related queries in real-time, cause online traffic and practically not possible. So, automatic answering system is helpful for answering product related queries. But, the product queries are always in product-explicit, so discovering related product queries and recovering its responds is distinctly be impractical. Accordingly, we propose Hierarchical Deep Neural Network (HiDeNN) model using MOQA framework to discern the appropriate reviews based on Mixtures of Opinions Question Answering (MOQA). The Hierarchical Deep Neural Network provides discerning the most relevant review for queries and it also provides the relevant answer for specific product category queries. The proposed method is executed on Python and it provides 9.594% and 7.574% higher accuracy value for Discerning Appropriate Reviews compared with the existing method like Relevant Reviews for Answering Product-related Queries (MOQA-BERTQA+FLTR+PT) and IQA: Interactive Query Construction on Semantic Question Answering Systems (IQC-SQA). The experimental result indicates that the proposed MOQA- HiDeNN method can efficiently and accurately get the optimal global solutions for recognizing the appropriate discerning of most relevant review for queries and it also provides the relevant answer for specific product category queries.

Music Data Feature Analysis and Extraction Algorithm Based on Music Melody Contour

Music is a way to reflect people’s real-life emotions, and listening to music has become an inseparable habit of the daily life. Text-based music information retrieval is still the main way for people to find music, but this method has obvious shortcomings and deficiencies, and it is a relatively cumbersome and inefficient method. In order to solve this problem, this paper proposes a feature extraction LAM algorithm based on the contour of music melody. Melody is the most important extraction feature in content-based music retrieval. Users can hum a song according to their own memory and then extract the rhythm, melody, and other information of the hummed audio information to match and identify the rhythm and melody features of the original song stored in the database. The retrieval method is based on the melody, rhythm, and other musical features of music and involves many issues such as the expression of musical melody, feature extraction of musical melody, user query construction, music melody matching, and music database construction. With the help of the customized query interface, media information can be retrieved. Finally, the experiment proves that the top-ten hit rate of the LAM algorithm after clustering is 91.3%, the top-three hit rate is 78.8%, and the first hit rate is 71.2%. The approximate symbol matching DP algorithm has a top-ten hit rate of 83.6%, a top-three hit rate of 66.4%, and a first hit rate of 63.6%. The method proposed in this paper has a high retrieval hit rate.

A Question Answering Framework Based on Hybridization of Deep Learning and Semantic Web Techniques

The question answering (QA) system has been existing for several years. QA systems are divided into different processes such as question processing, document processing, paragraph extraction, answer extraction, question analysis, phrase mapping, disambiguation, query construction, querying the Knowledge Base (KB), and result ordering on user response respectively. Based on these processes, many models have been developed using approaches ranging from linguistic, statistical, and pattern matching. Popular models are Feedback, Refinement and Extended VocabularY Aggregation (FREyA), PowerAqua, SemSek, Semantic Interpretation of User Queries for QA on Interlinked Data (SINA), DEep Answers for maNy Naturally Asked questions (DEANNA), gAnswer, SemGraph, OKBQA (Open Knowledge Base and Question Answering) and Semantic Question Answering (SQA), for performance evaluation, these mostly focus on higher precision, recall, and/or F-measure. However, most of these models are constrained in the following operations: the combination of knowledge bases from different sources, formalism for knowledge representation to support interoperability, optimization of query construction and generation, ranking of responses, and support for set operations (union, sorting, comparison, and aggregation on user query) during query generation. This research proposes a hybrid of recurrent neural network and semantic-web-based question answering as the (RNNSQA) framework that combines heterogeneous knowledge sources and improves on state-of-the-art query generation mechanisms to allow for integration of comprehensive question-type operations, and set-based operations listed above. First, there would be a combination of techniques that is Natural Language Processing (NLP) and Recurrent Neural Network (RNN) techniques in classifying questions into types. Secondly, the semantic web technique is then employed in generating (SPARQL Protocol and RDF (Resource Description Framework) Query Language) SPARQL-based candidate queries. The result of this study is an enhanced QA framework with improved query translation and construction capability.