Query Formulation Research Articles

An evaluation of a visual interface for supporting query formulation in scholarly searching

Performing an effective literature review is a fundamental academic skill. Whether writing up a final project, preparing a research proposal, or simply finding answers to complex questions, students need to be able to systematically gather and analyse evidence from a variety of sources. However, many students have difficulty formulating effective search queries and understanding how to optimise their search strategy. This paper evaluates a novel approach to query formulation based on an alternative, visual interface. The approach is evaluated alongside a conventional, form-based interface in a comparative, controlled setting. The study finds that overall, participants considered the visual interface to be more complex and difficult to use. However, at the same time they used significantly more terms, facets and reformulations in the visual interface, and gave more attention to creating and refining more complex queries. In addition, the majority considered the visual interface to have greater transparency, with a clearer overview of the search tasks that encouraged them to invest greater effort in completing them successfully. The results demonstrate that visual approaches can offer tangible benefits in developing and improving students’ competence in exploratory search tasks.

Bridging Data Models in Health Care With a Novel Intermediate Query Format for Feasibility Queries: Mixed Methods Study.

To advance research with clinical data, it is essential to make access to the available data as fast and easy as possible for researchers, which is especially challenging for data from different source systems within and across institutions. Over the years, many research repositories and data standards have been created. One of these is the Fast Healthcare Interoperability Resources (FHIR) standard, used by the German Medical Informatics Initiative (MII) to harmonize and standardize data across university hospitals in Germany. One of the first steps to make these data available is to allow researchers to create feasibility queries to determine the data availability for a specific research question. Given the heterogeneity of different query languages to access different data across and even within standards such as FHIR (eg, CQL and FHIR Search), creating an intermediate query syntax for feasibility queries reduces the complexity of query translation and improves interoperability across different research repositories and query languages. This study describes the creation and implementation of an intermediate query syntax for feasibility queries and how it integrates into the federated German health research portal (Forschungsdatenportal Gesundheit) and the MII. We analyzed the requirements for feasibility queries and the feasibility tools that are currently available in research repositories. Based on this analysis, we developed an intermediate query syntax that can be easily translated into different research repository-specific query languages. The resulting Clinical Cohort Definition Language (CCDL) for feasibility queries combines inclusion criteria in a conjunctive normal form and exclusion criteria in a disjunctive normal form, allowing for additional filters like time or numerical restrictions. The inclusion and exclusion results are combined via an expression to specify feasibility queries. We defined a JSON schema for the CCDL, generated an ontology, and demonstrated the use and translatability of the CCDL across multiple studies and real-world use cases. We developed and evaluated a structured query syntax for feasibility queries and demonstrated its use in a real-world example as part of a research platform across 39 German university hospitals.

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.

Harnessing AI for Enhanced Searching in Digital Libraries: Transforming Research Practices

The application of Artificial Intelligence (AI) technologies in digital libraries is changing the paradigm in which users search and interact with digital content. This article is focused on how the use of AI technologies improves the search in digital libraries, demonstrating the benefits of such technologies in overcoming the challenges associated with formulation of query, information retrieval, and end user usage. Most search engine systems face the problems of user queries, which are inherent in online searches. Many user queries are vague, imprecise or ambiguous with regards to the context and as a result lead to less than satisfactory search results. AI technologies such as Natural Language Processing (NLP) and Machine Learning (ML) solve this challenge effectively as they enhance comprehension of queries, contextual understanding, and relevance of the results returned. With the capabilities of NLP incorporated in search engines, search queries which are in the form of natural language can be understood and executed which leads to efficiency in targeting the information needed. Comprehensive restructuring of standard information systems is used by computer learning algorithms for searches by inference and instills usage in users. This study also examines the place of AI in query formulation and the different ways it can be employed; fully automated, semi-automated and/or manually so that the users are less faced with the challenges that are usually present during the query formulation process. Such increases in the level of difficulty and scope of information retrieval suggest that search AI improved the scenario.

ForestQB: Enhancing Linked Data Exploration through Graphical and Conversational UIs Integration

This article introduces the Forest Query Builder (ForestQB), an innovative toolkit designed to enhance the exploration and application of observational Linked Data (LD) within the field of wildlife research and conservation. Addressing the challenges faced by non-experts in navigating Resource Description Framework (RDF) triplestores and executing SPARQL queries, ForestQB employs a novel integrated approach. This approach combines a graphical user interface (GUI) with a conversational user interface (CUI), thereby greatly simplifying the process of query formulation and making observational LD accessible to users without expertise in RDF or SPARQL. Developed through insights derived from a comprehensive ethnographic study involving wildlife researchers, ForestQB is specifically designed to improve the accessibility of SPARQL endpoints and facilitate the exploration of observational LD in wildlife research contexts. To evaluate the effectiveness of our approach, we conducted a user experiment. The results of this evaluation affirm that ForestQB is not only efficient and user-friendly but also plays a crucial role in eliminating barriers for users, facilitating the effective use of observational LD in wildlife conservation and extending its benefits to wider domains. (GitHub Link: github.com/i3omar/ForestQB).

Evaluating the Efficacy of Large Language Models in CPT Coding for Craniofacial Surgery: A Comparative Analysis.

The advent of Large Language Models (LLMs) like ChatGPT has introduced significant advancements in various surgical disciplines. These developments have led to an increased interest in the utilization of LLMs for Current Procedural Terminology (CPT) coding in surgery. With CPT coding being a complex and time-consuming process, often exacerbated by the scarcity of professional coders, there is a pressing need for innovative solutions to enhance coding efficiency and accuracy. This observational study evaluated the effectiveness of 5 publicly available large language models-Perplexity.AI, Bard, BingAI, ChatGPT 3.5, and ChatGPT 4.0-in accurately identifying CPT codes for craniofacial procedures. A consistent query format was employed to test each model, ensuring the inclusion of detailed procedure components where necessary. The responses were classified as correct, partially correct, or incorrect based on their alignment with established CPT coding for the specified procedures. The results indicate that while there is no overall significant association between the type of AI model and the correctness of CPT code identification, there are notable differences in performance for simple and complex CPT codes among the models. Specifically, ChatGPT 4.0 showed higher accuracy for complex codes, whereas Perplexity.AI and Bard were more consistent with simple codes. The use of AI chatbots for CPT coding in craniofacial surgery presents a promising avenue for reducing the administrative burden and associated costs of manual coding. Despite the lower accuracy rates compared with specialized, trained algorithms, the accessibility and minimal training requirements of the AI chatbots make them attractive alternatives. The study also suggests that priming AI models with operative notes may enhance their accuracy, offering a resource-efficient strategy for improving CPT coding in clinical practice. This study highlights the feasibility and potential benefits of integrating LLMs into the CPT coding process for craniofacial surgery. The findings advocate for further refinement and training of AI models to improve their accuracy and practicality, suggesting a future where AI-assisted coding could become a standard component of surgical workflows, aligning with the ongoing digital transformation in health care.

[Translated article] The role of artificial intelligence in scientific publishing: perspectives from hospital pharmacy

The article examines the impact of artificial intelligence on scientific writing, with a particular focus on its application in hospital pharmacy. It analyses artificial intelligence tools that enhance information retrieval, literature analysis, writing quality, and manuscript drafting.Chatbots like Consensus, along with platforms such as Scite and SciSpace, enable precise searches in scientific databases, providing evidence-based responses and references. SciSpace facilitates the generation of comparative tables and the formulation of queries regarding studies, while ResearchRabbit maps the scientific literature to identify trends. Tools like DeepL and ProWritingAid improve writing quality by correcting grammatical, stylistic, and plagiarism errors. A.R.I.A. enhances reference management, and Jenny AI assists in overcoming writer's block. Python libraries such as langchain enable advanced semantic searches and the creation of agents.Despite their benefits, artificial intelligence raises ethical concerns including biases, misinformation, and plagiarism. The importance of responsible use and critical review by experts is emphasised. In hospital pharmacy, artificial intelligence can enhance efficiency and precision in research and scientific communication. Pharmacists can use these tools to stay updated, enhance the quality of their publications, optimise information management, and facilitate clinical decision-making.In conclusion, artificial intelligence is a powerful tool for hospital pharmacy, provided it is used responsibly and ethically.

Machine Advisors: Integrating Large Language Models Into Democratic Assemblies

ABSTRACT Could the employment of large language models (LLMs) in place of human advisors improve the problem-solving ability of democratic assemblies? LLMs represent the most significant recent incarnation of artificial intelligence and could change the future of democratic governance. This paper assesses their potential to serve as expert advisors to democratic representatives. While LLMs promise enhanced expertise availability and accessibility, they also present specific challenges. These include hallucinations, misalignment and value imposition. After weighing LLMs’ benefits and drawbacks against human advisors, I argue that time-tested democratic procedures, such as deliberation and aggregation by voting, provide safeguards that are effective against human and machine advisor shortcomings alike. Additional protective measures may include custom training for advisor LLMs or boosting representatives’ competencies in query formulation. Implementation of adversarial proceedings in which LLM advisors would debate each other and provide dissenting opinions is likely to yield further epistemic benefits. Overall, promising interventions that would mitigate the LLM risks appear feasible. Machine advisors could thus empower human decision-makers to make more autonomous, higher-quality decisions. On this basis, I defend the hypothesis that LLMs’ careful integration into policymaking could augment democracy’s ability to address today’s complex social problems.

TransFOL: A Logical Query Model for Complex Relational Reasoning in Drug-Drug Interaction.

Predicting drug-drug interaction (DDI) plays a crucial role in drug recommendation and discovery. However, wet lab methods are prohibitively expensive and time-consuming due to drug interactions. In recent years, deep learning methods have gained widespread use in drug reasoning. Although these methods have demonstrated effectiveness, they can only predict the interaction between a drug pair and do not contain any other information. However, DDI is greatly affected by various other biomedical factors (such as the dose of the drug). As a result, it is challenging to apply them to more complex and meaningful reasoning tasks. Therefore, this study regards DDI as a link prediction problem on knowledge graphs and proposes a DDI prediction model based on Cross-Transformer and Graph Convolutional Networks (GCNs) in first-order logical query form, TransFOL. In the model, a biomedical query graph is first built to learn the embedding representation. Subsequently, an enhancement module is designed to aggregate the semantics of entities and relations. Cross-Transformer is used for encoding to obtain semantic information between nodes, and GCN is used to gather neighbour information further and predict inference results. To evaluate the performance of TransFOL on common DDI tasks, we conduct experiments on two benchmark datasets. The experimental results indicate that our model outperforms state-of-the-art methods on traditional DDI tasks. Additionally, we introduce different biomedical information in the other two experiments to make the settings more realistic. Experimental results verify the strong drug reasoning ability and generalization of TransFOL in complex settings.

The method of linear-logical operators and logical equations in information extraction tasks

Relational and logical methods of knowledge representation play a key role in creating a mathematical basis for information systems. Predicate algebra and predicate operators are among the most effective tools for describing information in detail. These tools make it easy to formulate formalized information, create database queries, and simulate human activity. In the context of the new need for reliable and efficient data selection, a problem arises in deeper analysis. Subject of the study is the theory of quantum linear equations based on the algebra of linear predicate operations, the formal apparatus of linear logic operators and methods for solving logical equations in information extraction tasks. Aim of the study is a developing of a method for using linear logic operators and logical equations to extract information. This approach can significantly optimize the process of extracting the necessary information, even in huge databases. Main tasks: analysis of existing approaches to information extraction; consideration of the theory of linear logic operators; study of methods for reducing logic to an algebraic form; analysis of logical spaces and the algebra of finite predicate actions and the theory of linear logic operators. The research methods involve a systematic analysis of the mathematical structure of the algebra of finite predicates and predicate functions to identify the key elements that affect the query formation process. The method of using linear logic operators and logical equations for information extraction is proposed. The results of the study showed that the method of using linear logic operators and logical equations is a universal and adaptive tool for working with algebraic data structures. It can be applied in a wide range of information extraction tasks and prove its value as one of the possible methods of information processing. Conclusion. The paper investigates formal methods of intelligent systems, in particular, ways of representing knowledge in accordance with the peculiarities of the field of application and the language that allows encoding this knowledge for storage in computer memory. The proposed method can be implemented in the development of language interfaces for automated information access systems, in search engine algorithms, for logical analysis of information in databases and expert systems, as well as in performing tasks related to object recognition and classification.

Construction of a model for matching user's linguistic structures to a chat-bot language model

The research object of this work is the linguistic structures of the user when constructing a request to a chatbot with generative artificial intelligence. The study solved the task of improving the communication mediation algorithms of chatbots through the comparison models of linguistic structures by users. Sometimes the user intentionally or due to lack of information forms an inaccurate request. Formally, this is described by logical operations "And" and "And or Not". As a result of the research, a model was built comparing linguistic structures at the input with the information model of the response at the output. The model was based on an approach with recursive creation of an answer. That has made it possible to determine the basic characteristics of the object of the request and form an answer on this basis. Using this approach improved the accuracy of the chatbot response. It also made it possible to consider the linguistic structure of the user through its formalization. The use of logic algebra made it possible to find typical errors of users during dialogs with generative artificial intelligence. A feature of the reported advancement is that the comparison of models of linguistic structures of query formation is carried out through a recurrent algorithm. As a result, it makes it possible to compare the query in such a way as to reduce the absolute error of the primary data by 0.02 % and simplify the process of mathematical calculations. At the same time, the received information becomes more accurate – the number of references increases from 2 to 6 sources. The proposal could be used in practical activities to improve the natural language recognition technologies of users in chatbots with generative artificial intelligence. On this basis, it is possible to devise various applications and services for training and practical activities

El rol de la inteligencia artificial en la publicación científica: perspectivas desde la farmacia hospitalaria

The article examines the impact of artificial intelligence on scientific writing, with a particular focus on its application in hospital pharmacy. It analyzes artificial intelligence tools that enhance information retrieval, literature analysis, writing quality, and manuscript drafting.Chatbots like Consensus, along with platforms such as Scite and SciSpace, enable precise searches in scientific databases, providing evidence-based responses and references. SciSpace facilitates the generation of comparative tables and the formulation of queries regarding studies, while ResearchRabbit maps the scientific literature to identify trends. Tools like DeepL and ProWritingAid improve writing quality by correcting grammatical, stylistic, and plagiarism errors. A.R.I.A. enhances reference management, and Jenny AI assists in overcoming writer's block. Python libraries such as LangChain enable advanced semantic searches and the creation of agents.Despite their benefits, artificial intelligence raises ethical concerns including biases, misinformation, and plagiarism. The importance of responsible use and critical review by experts is emphasized. In hospital pharmacy, artificial intelligence can enhance efficiency and precision in research and scientific communication. Pharmacists can use these tools to stay updated, enhance the quality of their publications, optimize information management, and facilitate clinical decision-making.In conclusion, artificial intelligence is a powerful tool for hospital pharmacy, provided it is used responsibly and ethically.

Query-Oriented Micro-Video Summarization.

Query-oriented micro-video summarization task aims to generate a concise sentence with two properties: (a) summarizing the main semantic of the micro-video and (b) being expressed in the form of search queries to facilitate retrieval. Despite its enormous application value in the retrieval area, this direction has barely been explored. Previous studies of summarization mostly focus on the content summarization for traditional long videos. Directly applying these studies is prone to gain unsatisfactory results because of the unique features of micro-videos and queries: diverse entities and complex scenes within a short time, semantic gaps between modalities, and various queries in distinct expressions. To specifically adapt to these characteristics, we propose a query-oriented micro-video summarization model, dubbed QMS. It employs an encoder-decoder-based transformer architecture as the skeleton. The multi-modal (visual and textual) signals are passed through two modal-specific encoders to obtain their representations, followed by an entity-aware representation learning module to identify and highlight critical entity information. As to the optimization, regarding the large semantic gaps between modalities, we assign different confidence scores according to their semantic relevance in the optimization process. Additionally, we develop a novel strategy to sample the effective target query among the diverse query set with various expressions. Extensive experiments demonstrate the superiority of the QMS scheme, on both the summarization and retrieval tasks, over several state-of-the-art methods.

Searching COVID-19 Clinical Research Using Graph Queries: Algorithm Development and Validation.

Since the beginning of the COVID-19 pandemic, >1 million studies have been collected within the COVID-19 Open Research Dataset, a corpus of manuscripts created to accelerate research against the disease. Their related abstracts hold a wealth of information that remains largely unexplored and difficult to search due to its unstructured nature. Keyword-based search is the standard approach, which allows users to retrieve the documents of a corpus that contain (all or some of) the words in a target list. This type of search, however, does not provide visual support to the task and is not suited to expressing complex queries or compensating for missing specifications. This study aims to consider small graphs of concepts and exploit them for expressing graph searches over existing COVID-19-related literature, leveraging the increasing use of graphs to represent and query scientific knowledge and providing a user-friendly search and exploration experience. We considered the COVID-19 Open Research Dataset corpus and summarized its content by annotating the publications' abstracts using terms selected from the Unified Medical Language System and the Ontology of Coronavirus Infectious Disease. Then, we built a co-occurrence network that includes all relevant concepts mentioned in the corpus, establishing connections when their mutual information is relevant. A sophisticated graph query engine was built to allow the identification of the best matches of graph queries on the network. It also supports partial matches and suggests potential query completions using shortest paths. We built a large co-occurrence network, consisting of 128,249 entities and 47,198,965 relationships; the GRAPH-SEARCH interface allows users to explore the network by formulating or adapting graph queries; it produces a bibliography of publications, which are globally ranked; and each publication is further associated with the specific parts of the query that it explains, thereby allowing the user to understand each aspect of the matching. Our approach supports the process of query formulation and evidence search upon a large text corpus; it can be reapplied to any scientific domain where documents corpora and curated ontologies are made available.

Unstructured Data Fusion for Schema and Data Extraction

Recently, there has been significant interest in extracting actionable insights from the abundance of unstructured textual data. In this paper, we introduce a novel problem, which we term Semistructured Schema and Data Extraction (SDE). This task aims to enhance and complete tables using information discovered from textual repositories, given partial table specifications in the form of queries. To effectively solve SDE, several challenges must be overcome, which involve transforming the partial table specifications into effective queries, retrieving relevant documents, discerning values for partially specified attributes, inferring additional attributes, and constructing an enriched output table while mitigating the influence of false positives from the retrieval. We propose an end-to-end pipeline for SDE, which consists of a retrieval component and an augmentation component, to address each of the challenges. In the retrieval component, we serialize the partial table specifications into a query and employ a dense passage retrieval algorithm to extract the top-k relevant results from the text repository. Subsequently, the augmentation component ingests the output documents from the retrieval phase and generates an enriched table. We formulate this table enrichment task as a unique sequence-to-sequence task, distinct from traditional approaches, as it operates on multiple documents during generation. Utilizing an interpolation mechanism on the encoder output, our model maintains a nearly constant context length while automatically prioritizing the importance of documents during the generation. Due to the novelty of SDE, we establish a validation methodology, adapting and expanding existing benchmarks with the use of powerful large language models. Our extensive experiments show that our method achieves high accuracy in enriching query tables through multi-document fusion, while also surpassing baseline methods in both accuracy and computational efficiency.

Entity Footprinting: Modeling Contextual User States via Digital Activity Monitoring

Our digital life consists of activities that are organized around tasks and exhibit different user states in the digital contexts around these activities. Previous works have shown that digital activity monitoring can be used to predict entities that users will need to perform digital tasks. There have been methods developed to automatically detect the tasks of a user. However, these studies typically support only specific applications and tasks, and relatively little research has been conducted on real-life digital activities. This article introduces user state modeling and prediction with contextual information captured as entities, recorded from real-world digital user behavior, called entity footprinting —a system that records users’ digital activities on their screens and proactively provides useful entities across application boundaries without requiring explicit query formulation. Our methodology is to detect contextual user states using latent representations of entities occurring in digital activities. Using topic models and recurrent neural networks, the model learns the latent representation of concurrent entities and their sequential relationships. We report a field study in which the digital activities of 13 people were recorded continuously for 14 days. The model learned from this data is used to (1) predict contextual user states and (2) predict relevant entities for the detected states. The results show improved user state detection accuracy and entity prediction performance compared to static, heuristic, and basic topic models. Our findings have implications for the design of proactive recommendation systems that can implicitly infer users’ contextual state by monitoring users’ digital activities and proactively recommending the right information at the right time.

Large language models facilitate the generation of electronic health record phenotyping algorithms.

Phenotyping is a core task in observational health research utilizing electronic health records (EHRs). Developing an accurate algorithm demands substantial input from domain experts, involving extensive literature review and evidence synthesis. This burdensome process limits scalability and delays knowledge discovery. We investigate the potential for leveraging large language models (LLMs) to enhance the efficiency of EHR phenotyping by generating high-quality algorithm drafts. We prompted four LLMs-GPT-4 and GPT-3.5 of ChatGPT, Claude 2, and Bard-in October 2023, asking them to generate executable phenotyping algorithms in the form of SQL queries adhering to a common data model (CDM) for three phenotypes (ie, type 2 diabetes mellitus, dementia, and hypothyroidism). Three phenotyping experts evaluated the returned algorithms across several critical metrics. We further implemented the top-rated algorithms and compared them against clinician-validated phenotyping algorithms from the Electronic Medical Records and Genomics (eMERGE) network. GPT-4 and GPT-3.5 exhibited significantly higher overall expert evaluation scores in instruction following, algorithmic logic, and SQL executability, when compared to Claude 2 and Bard. Although GPT-4 and GPT-3.5 effectively identified relevant clinical concepts, they exhibited immature capability in organizing phenotyping criteria with the proper logic, leading to phenotyping algorithms that were either excessively restrictive (with low recall) or overly broad (with low positive predictive values). GPT versions 3.5 and 4 are capable of drafting phenotyping algorithms by identifying relevant clinical criteria aligned with a CDM. However, expertise in informatics and clinical experience is still required to assess and further refine generated algorithms.

Enhancing Query Formulation for Universal Image Segmentation.

Recent advancements in image segmentation have been notably driven by Vision Transformers. These transformer-based models offer one versatile network structure capable of handling a variety of segmentation tasks. Despite their effectiveness, the pursuit of enhanced capabilities often leads to more intricate architectures and greater computational demands. OneFormer has responded to these challenges by introducing a query-text contrastive learning strategy active during training only. However, this approach has not completely addressed the inefficiency issues in text generation and the contrastive loss computation. To solve these problems, we introduce Efficient Query Optimizer (EQO), an approach that efficiently utilizes multi-modal data to refine query optimization in image segmentation. Our strategy significantly reduces the complexity of parameters and computations by distilling inter-class and inter-task information from an image into a single template sentence. Furthermore, we propose a novel attention-based contrastive loss. It is designed to facilitate a one-to-many matching mechanism in the loss computation, which helps object queries learn more robust representations. Beyond merely reducing complexity, our model demonstrates superior performance compared to OneFormer across all three segmentation tasks using the Swin-T backbone. Our evaluations on the ADE20K dataset reveal that our model outperforms OneFormer in multiple metrics: by 0.2% in mean Intersection over Union (mIoU), 0.6% in Average Precision (AP), and 0.8% in Panoptic Quality (PQ). These results highlight the efficacy of our model in advancing the field of image segmentation.

A semi-supervised learning approach for semantic parsing boosted by BERT word embedding

In the modern world, structured and semi-structured knowledge bases hold a considerable amount of data. There-fore, people who are familiar with formal query languages should not be the only ones who can efficiently and clearly query them. Semantic Parsing (SP) is converting natural language utterances into formal meaning representations. The paper suggests a model for SP that uses a novel method of utilizing the Semi-Supervised Generative Adversarial Network (SS-GAN) to enhance the classifier performance. The proposed SS-GAN extends the fine-tuning of word embedding architectures using unlabeled examples in a generative adversarial environment. We provide a regularization strategy for addressing the mode missing problem and unstable training in SS-GAN. The main viewpoint is to use the extracted feature vectors from the discriminator. Hence, the generator produces outputs by aiding the discriminator’s learned features. A reconstruction loss is added to the loss function of the SS-GAN to drive the genera-tor to reconstruct outputs from the discriminator’s features, hence steering the generator toward actual data configurations. The proposed reconstruction loss improves the performance of SS-GAN, produces high-quality outputs, and may be combined with other regularization loss functions to improve the performance of diverse GANs. We employ BERT word embedding for our model, which can be included in a downstream task and fine-tuned as a model, while the pre-trained BERT model can capture various linguistic properties. We examine the suggested model using the WikiSQL and SparC datasets, and the analysis findings reveal our model outperforms its rivals. The findings from our experiments indicate that the need for labeled samples can be minimized, down to as few as 100 instances, while still achieving commendable classification outcomes.

Structured Queries to AQL: Querying OpenEHR Data Leveraging a FHIR-Based Infrastructure for Federated Feasibility Queries.

In digital healthcare, data heterogeneity is a reoccurring issue caused by proprietary source systems. It is often overcome by utilizing ETL processes resulting in data warehouses, which ensure common data models for interoperability. Unfortunately, the achieved interoperability is usually limited to an institutional level. The broad solution space to achieve interoperability with different health data standards is part of the problem, resulting in different standards used at various institutions. For cross-institutional use cases like federated feasibility queries, the issue of heterogeneity is reintroduced. This work showcases how the existing German infrastructure for federated feasibility queries based on Hl7 FHIR can be extended to support openEHR without further data transformation. By utilizing an intermediate query format that can be transferred to FHIR Search, CQL, and AQL.