Answer Complex Queries Research Articles

Comparison of ChatGPT-3.5, ChatGPT-4, and Orthopaedic Resident Performance on Orthopaedic Assessment Examinations.

Artificial intelligence (AI) programs have the ability to answer complex queries including medical profession examination questions. The purpose of this study was to compare the performance of orthopaedic residents (ortho residents) against Chat Generative Pretrained Transformer (ChatGPT)-3.5 and GPT-4 on orthopaedic assessment examinations. A secondary objective was to perform a subgroup analysis comparing the performance of each group on questions that included image interpretation versus text-only questions. The ResStudy orthopaedic examination question bank was used as the primary source of questions. One hundred eighty questions and answer choices from nine different orthopaedic subspecialties were directly input into ChatGPT-3.5 and then GPT-4. ChatGPT did not have consistently available image interpretation, so no images were directly provided to either AI format. Answers were recorded as correct versus incorrect by the chatbot, and resident performance was recorded based on user data provided by ResStudy. Overall, ChatGPT-3.5, GPT-4, and ortho residents scored 29.4%, 47.2%, and 74.2%, respectively. There was a difference among the three groups in testing success, with ortho residents scoring higher than ChatGPT-3.5 and GPT-4 ( P < 0.001 and P < 0.001). GPT-4 scored higher than ChatGPT-3.5 ( P = 0.002). A subgroup analysis was performed by dividing questions into question stems without images and question stems with images. ChatGPT-3.5 was more correct (37.8% vs. 22.4%, respectively, OR = 2.1, P = 0.033) and ChatGPT-4 was also more correct (61.0% vs. 35.7%, OR = 2.8, P < 0.001), when comparing text-only questions versus questions with images. Residents were 72.6% versus 75.5% correct with text-only questions versus questions with images, with no significant difference ( P = 0.302). Orthopaedic residents were able to answer more questions accurately than ChatGPT-3.5 and GPT-4 on orthopaedic assessment examinations. GPT-4 is superior to ChatGPT-3.5 for answering orthopaedic resident assessment examination questions. Both ChatGPT-3.5 and GPT-4 performed better on text-only questions than questions with images. It is unlikely that GPT-4 or ChatGPT-3.5 would pass the American Board of Orthopaedic Surgery written examination.

Brain-Inspired Search Engine Assistant Based on Knowledge Graph.

Search engines can quickly respond to a hyperlink list according to query keywords. However, when a query is complex, developers need to repeatedly refine search keywords and open a large number of web pages to find and summarize answers. Many research works of question and answering (Q&A) system attempt to assist search engines by providing simple, accurate, and understandable answers. However, without original semantic contexts, these answers lack explainability, making them difficult for users to trust and adopt. In this article, a brain-inspired search engine assistant named DeveloperBot based on knowledge graph is proposed, which aligns to the cognitive process of humans and has the capacity to answer complex queries with explainability. Specifically, DeveloperBot first constructs a multilayer query graph by splitting a complex multiconstraint query into several ordered constraints. Then, it models a constraint reasoning process as a subgraph search process inspired by a spreading activation model of cognitive science. In the end, novel features of the subgraph are extracted for decision-making. The corresponding reasoning subgraph and answer confidence are derived as explanations. The results of the decision-making demonstrate that DeveloperBot can estimate answers and answer confidences with high accuracy. We implement a prototype and conduct a user study to evaluate whether and how the direct answers and the explanations provided by DeveloperBot can assist developers' information needs.

Efficient Embeddings of Logical Variables for Query Answering over Incomplete Knowledge Graphs

The problem of answering complex First-order Logic queries over incomplete knowledge graphs is receiving growing attention in the literature. A promising recent approach to this problem has been to exploit neural link predictors, which can be effective in identifying individual missing triples in the incomplete graph, in order to efficiently answer complex queries. A crucial advantage of this approach over other methods is that it does not require example answers to complex queries for training, as it relies only on the availability of a trained link predictor for the knowledge graph at hand. This approach, however, can be computationally expensive during inference, and cannot deal with queries involving negation. In this paper, we propose a novel approach that addresses all of these limitations. Experiments on established benchmark datasets demonstrate that our approach offers superior performance while significantly reducing inference times.

Diffusion-Based Influence Maximization in GOLAP

Influence analysis is one of the most important research in social network. Specifically, more and more researchers and advertisers are interested in the area of influence maximization (IM). The concept of influence among people or organizations has been the core basis for making business decisions as well as performing everyday social activities.In this research, we begin by extending a new influence diffusion model information diffusion model (IDM) using various constraints. We incorporate colors and additional nodes constraints. By adding colors and constraints for different types of nodes in a graph, we would be able to answer complex queries on multi-dimensional graphs such as ‘find at most two most important genes that are related to lung disease and heart disease’. More specifically, we discuss the following variations of IM-IDM; Colorblind IM-IDM, Colored IM-IDM and Colored IM-IDM with constraints. We also present our experiment results to prove the effectiveness of our model and algorithms.

Answering Complex Queries in an Online Community Network

An online community network such as Twitter or amazon.com links entities (e.g., users, products) with various relationships (e.g., friendship, co-purchase) and make such information available for access through a web interface. The web interfaces of these networks often support features such as keyword search and "get-neighbors" — so a visitor can quickly find entities (e.g., users/products) of interest. Nonetheless, the interface is usually too restrictive to answer complex queries such as (1) find 100 Twitter users from California with at least 100 followers who talked about ICWSM last year or (2) find 100 books with at least 200 5-star reviews at amazon.com. In this paper, we introduce the novel problem of answering complex queries that involve non-searchable attributes through the web interface of an online community network. We model such a network as a heterogeneous graph with two access channels, Content Search and Local Search. We propose a unified approach that transforms the complex query into a small number of supported ones based on a strategic query-selection process. We conduct comprehensive experiments on Twitter and amazon.com which demonstrate the efficacy of our proposed algorithms.

Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders

Representation learning for knowledge graphs (KGs) has focused on the problem of answering simple link prediction queries. In this work we address the more ambitious challenge of predicting the answers of conjunctive queries with multiple missing entities. We propose Bidirectional Query Embedding (BiQE), a method that embeds conjunctive queries with models based on bi-directional attention mechanisms. Contrary to prior work, bidirectional self-attention can capture interactions among all the elements of a query graph. We introduce two new challenging datasets for studying conjunctive query inference and conduct experiments on several benchmark datasets that demonstrate BiQE significantly outperforms state of the art baselines.

Querying XML documents using Prolog engines: When is this a good idea?

XML has become a universal standard for information exchange over the Web due to features such as simple syntax and extensibility. Processing queries over these documents has been the focus of several research groups. In fact, there is broad literature in efficient XML query processing which explore indexes, fragmentation techniques, etc. However, for answering complex queries, existing approaches mainly analyze information that is explicitly defined in the XML document. A few work investigate the use of Prolog to increase the query possibilities, allowing inference over the data content. This can cause a significant increase in the query possibilities and expressive power, allowing access to non-obvious information. However, this requires translating the XML documents into Prolog facts. But for regular queries (which do not require inference), is this a good alternative? What kind of queries could benefit from the Prolog translation? Can we always use Prolog engines to execute XML queries in an efficient way? There are many questions involved in adopting an alternative approach to run XML queries. In this work, we investigate this matter by translating XML queries into Prolog queries and comparing the query processing times using Prolog and native XML engines. Our work contributes by providing a set of heuristics that helps users to decide when to use Prolog engines to process a given XML query. In summary, our results show that queries that search elements by a key value or by its position (simple search) are more efficient when run in Prolog than in native XML engines. Also, queries over large datasets, or that searches for substrings perform better when run by native XML engines.

Communication-Efficient Data Aggregation Tree Construction for Complex Queries in IoT Applications

Data aggregation is a fundamental operation in Internet of Things (IoT) applications, e.g., distributed Internet-based industrial control and computing systems. As IoT devices are increasingly connected to the system via resource-constrained wireless communication links, it is critical to perform communication-efficient data aggregation to answer complex queries (e.g., skyline queries and equality joins) from IoT applications. In this paper, we investigate the problem of constructing an aggregation tree (AT) for complex queries with the minimum communication cost. As complex queries have a dynamic size of intermediate results, existing Steiner tree-based approaches for traditional query operators, e.g., MIN and top- ${k}$ , cannot be directly applied. We first formalize the aggregation gain by jointly considering the data pruning power (the size of data points that can be pruned during the aggregation for complex queries) and aggregation cost (the size of data points transmitted for the aggregation). By maximizing the aggregation gain, the data set that has a higher pruning power and a smaller size is selected and transferred for data aggregation at succeeding nodes. We then propose to construct the AT by connecting a set of aggregation operations with maximum aggregation gain. Extensive evaluation shows that our proposed framework achieves the promising results.

Research Trends in Surveillance through Sousveillance

Collective Intelligence is an immense research area that has wide application to cross-disciplines, like social, legal, and computation. Research trends in Surveillance find its place in the work of this area generating curated data set helpful in answering complex queries. Sousveillance is a recent term coined by researchers and had been discussed in different literatures. However our findings suggest that integration of Surviellance through Sousviellance data set has not been given much importance in collective fashion. In this literature we introduced an effective model of collective intelligence by integrating surveillance through sousviellance in a campus environment. For testbed networking devices are used to generate sousvillance data to provide validation, and cleaning to enable reliability and trust in the target object.

Connection Scan Algorithm

We introduce the Connection Scan Algorithm (CSA) to efficiently answer queries to timetable information systems. The input consists, in the simplest setting, of a source position and a desired target position. The output consists of a sequence of vehicles such as trains or buses that a traveler should take to get from the source to the target. We study several problem variations such as the earliest arrival and profile problems. We present algorithm variants that only optimize the arrival time or additionally optimize the number of transfers in the Pareto sense. An advantage of CSA is that it can easily adjust to changes in the timetable, allowing the easy incorporation of known vehicle delays. We additionally introduce the Minimum Expected Arrival Time (MEAT) problem to handle possible, uncertain, future vehicle delays. We present a solution to the MEAT problem that is based on CSA. Finally, we extend CSA using the multilevel overlay paradigm to answer complex queries on nationwide integrated timetables with trains and buses.

Towards a grapho-phonologically parsed corpus of medieval Scots: database design and technical solutions

This paper presents a newly constructed corpus of sound-to-spelling mappings in medieval Scots, which stems from the work of the From Inglis to Scots (FITS) project. We have developed a systematic approach to the relationships between individual spellings and proposed sound values, and recorded these mutual links in a relational database. In this paper, we introduce the theoretical underpinnings of sound-to-spelling and spelling-to-sound mappings, and show how a Scots root morpheme undergoes grapho-phonological parsing, the analytical procedure that is employed to break down spelling sequences into sound units. We explain the data collection and annotation for the FITS Corpus (Alcorn et al., forthcoming), drawing attention to the extensive meta-data which accompany each analysed unit of spelling and sound. The database records grammatical and lexical information about the root, the positional arrangement of segments within the root, labels for the nuclei, vowels and consonants, the morphological context, and extra-linguistic detail of the text a given root was taken from (date, place and text type). With this wealth of information, the FITS corpus is capable of answering complex queries about the sound and spelling systems of medieval Scots. We also suggest how our methodology can be transferred to other non-standardised spelling systems.

POSTER

Large-scale graphs are becoming critical in various domains such as social network, scientific application, knowledge discovery, and even system software, etc. Many of those use cases require large-scale high-performance graph databases, which are designed for serving continuous updates from the clients, and at the same time, answering complex queries towards the current graph in an on-line manner. Those operations in graph databases, also referred as OLTP (online transaction processing) operations, need specific design and implementation in graph partitioning algorithms. In this study, we designed an incremental online graph partitioning (IOGP), optimized for OLTP workloads. It is designed to achieve better locality, generate balanced partitions, and increase the parallelism for accessing hotspots of the graph. Our evaluation results on both real world and synthetic graphs in both simulation and real system confirm a better performance on graph queries (as much as 2X) with small overheads during graph insertion (less than 10%).

Quantifying the Connectivity of a Semantic Warehouse and Understanding its Evolution over Time

In many applications one has to fetch and assemble pieces of information coming from more than one source for building a semantic warehouse offering more advanced query capabilities. In this paper the authors describe the corresponding requirements and challenges, and they focus on the aspects of quality and value of the warehouse. For this reason they introduce various metrics (or measures) for quantifying its connectivity, and consequently its ability to answer complex queries. The authors demonstrate the behaviour of these metrics in the context of a real and operational semantic warehouse, as well as on synthetically produced warehouses. The proposed metrics allow someone to get an overview of the contribution (to the warehouse) of each source and to quantify the value of the entire warehouse. Consequently, these metrics can be used for advancing data/endpoint profiling and for this reason the authors use an extension of VoID (for making them publishable). Such descriptions can be exploited for dataset/endpoint selection in the context of federated search. In addition, the authors show how the metrics can be used for monitoring a semantic warehouse after each reconstruction reducing thereby the cost of quality checking, as well as for understanding its evolution over time.

QuERy

This paper explores an analysis-aware data cleaning architecture for a large class of SPJ SQL queries. In particular, we propose QuERy, a novel framework for integrating entity resolution (ER) with query processing. The aim of QuERy is to correctly and efficiently answer complex queries issued on top of dirty data. The comprehensive empirical evaluation of the proposed solution demonstrates its significant advantage in terms of efficiency over the traditional techniques for the given problem settings.

SWI: A Semantic Web Interactive Gazetteer to support Linked Open Data

Current implementations of gazetteers, geographic directories that associate place names to geographic coordinates, cannot use semantics to answer complex queries (most gazetteers are just thesauri of place names), use domain ontologies for place name disambiguation, make their data sets available in the Semantic Web or support the use of Volunteered Geographic Information (VGI). A new generation of gazetteers has to tackle these problems. In this paper, we present a new architecture for gazetteers that uses VGI and Semantic Web tools, such as ontologies and Linked Open Data to overcome these limitations. We also present a gazetteer, the Semantic Web Interactive Gazetteer (SWI), implemented using this architecture, and show that it can be used to add absent geographic coordinates to biodiversity records. In our tests, we use this gazetteer to correct geographic data from a big sample (around 142,000 occurrence records of Amazonian specimens) from SpeciesLink, a big repository of biodiversity collection records from Brazil. The tests showed that the SWI Gazetteer was able to add geographic coordinates to around 30,000 records, increasing the records with coordinates from 30.29% to 57.5% of the total number of records in the sample (representing an increase of 90%).

A System Architecture for Heterogeneous Moving-Object Trajectory Metamodel Using Generic Sensors: Tracking Airport Security Case Study

This paper proposes a system architecture and case study for a heterogeneous moving-object trajectory metamodel using generic sensors. In order to provide a unified metamodel and powerful framework for trajectory's services and queries, the proposed trajectory's data model has benefited from advantages of both conceptual and ontological space-time. However, it extends the basic data model of trajectory with new patterns as the space-time path to describe activities of the moving object and the composite region of interest. Additionally, the proposed system is distinguished by providing a framework for dealing with moving-object trajectory in an interoperable way, using heterogonous sensors that traditional data model incapable for this purpose. The proposed system architecture for the moving-object trajectory's data model is focused on service composability and data interoperability combining Open Geospatial Consortium (OGC) standards, Service-Oriented Architecture, and streaming technology, to allow applications built using the framework to be scalable and have better performance. The case study presented for tracking travelers at the airport means that passenger locations can be determined with a higher degree of accuracy and precision. Indeed, this system makes it easy to answer complex queries, such as seeing closely where passengers congregate, how much time they spend in stores and restaurants, and where there may be bottlenecks. It will also enable airport retailers to communicate with travelers directly.

Answering regular path queries in expressive Description Logics via alternating tree-automata

Expressive Description Logics (DLs) have been advocated as formalisms for modeling the domain of interest in various application areas, including the Semantic Web, data and information integration, peer-to-peer data management, and ontology-based data access. An important requirement there is the ability to answer complex queries beyond instance retrieval, taking into account constraints expressed in a knowledge base. We consider this task for positive 2-way regular path queries (P2RPQs) over knowledge bases in the expressive DL ZIQ. P2RPQs are more general than conjunctive queries, union of conjunctive queries, and regular path queries from the literature. They allow regular expressions over roles and data joins that require inverse paths. The DL ZIQ extends the core DL ALC with qualified number restrictions, inverse roles, safe Boolean role expressions, regular expressions over roles, and concepts of the form ∃S.Self in the style of the DL SRIQ. Using techniques based on two-way tree-automata, we first provide as a stepping stone an elegant characterization of TBox and ABox satisfiability testing which gives us a tight ExpTime bound for this problem (under unary number encoding). We then establish a double exponential upper bound for answering P2RPQs over ZIQ knowledge bases; this bound is tight. Our result significantly pushes the frontier of 2ExpTime decidability of query answering in expressive DLs, both with respect to the query language and the considered DL. Furthermore, by reducing the well known DL SRIQ to ZIQ (with an exponential blow-up in the size of the knowledge base), we also provide a tight 2ExpTime upper bound for knowledge base satisfiability in SRIQ and establish the decidability of query answering for this significant fragment of the new OWL 2 standard.

A framework for processing complex queries in wireless sensor networks

In this work, we present a framework, denoted ADAGA -- P *, for processing complex queries and for managing sensor-field regression models. The proposed mechanism builds and instantiates sensor-field models. Thus ADAGA -- P * makes query engines able to answer complex queries such as give the probability of rain for the next two days in the city of Fortaleza . On the other hand, it is well known that minimizing energy consumption in a Wireless Sensor Network (WSN) is a critical issue for increasing the network lifetime. An efficient strategy for saving power in WSNs is to reduce the data volume injected into the network. For that reason, ADAGA -- P * implements an in-network data prediction mechanism in order to avoid that all sensed data have to be sent to fusion center node (or base station). Thus, sensor nodes only transmit data which are novelties for a regression model applied by ADAGA -- P *. Experiments using real data have been executed to validate our approach. The results show that ADAGA -- P * is quite efficient regarding communication cost and the number of executed float-point operations. In fact, the energy consumption rate to run ADAGA -- P * is up to 14 times lower than the energy consumed by kernel distributed regression for an RMSE difference of 0.003.

BioQuery-ASP: querying biomedical databases and ontologies using answer set programming

Motivation and Objectives Storing biomedical data in various structured forms, like biomedical databases or ontologies, and at different locations have brought about many challenges for answering complex queries about the knowledge represented in these resources. For instance, here are two queries about some genes, drugs and diseases: “What are the drugs that treat the disease Depression and that do not target the gene ACYP1?”, “What are the 3 most similar drugs that target the gene DLG4?” One of the challenges of answering such complex queries is to represent the queries in a natural language and present the answers in an understandable form. Another challenge is to efficiently find answers to complex queries that require appropriate integration of relevant knowledge stored in different places and in various forms, and/or that require auxiliary definitions, such as, chains of drug-drug interactions, cliques of genes based on gene-gene relations, similarity/diversity of genes/drugs. Furthermore, once an answer is found for a complex query, the experts may need further explanations about the answer. We have developed novel computational methods and built a software system, called BioQuery-ASP, to handle all these challenges

Finding Answers and Generating Explanations for Complex Biomedical Queries

We present new methods to efficiently answer complex queries overbiomedical ontologies and databases considering the relevant partsof these knowledge resources, and to generate shortest explanationsto justify these answers. Both algorithms rely on the high-levelrepresentation and efficient solvers of Answer Set Programming. Weapply these algorithms to find answers and explanations to some complexqueries related to drug discovery, over PharmGKB, DrugBank, BioGrid, CTD and Sider.