Knowledge Retrieval Research Articles

Zero-Shot Construction of Chinese Medical Knowledge Graph with GPT-3.5-turbo and GPT-4

Knowledge graphs have revolutionized the organization and retrieval of real-world knowledge, prompting interest in automatic NLP-based approaches for extracting medical knowledge from texts. However, the availability of high-quality Chinese medical knowledge remains limited, posing challenges for constructing Chinese medical knowledge graphs. As LLMs like ChatGPT show promise in zero-shot learning for many NLP downstream tasks, their potential on constructing Chinese medical knowledge graphs is still uncertain. In this study, we create a Chinese medical knowledge graph by manually annotating textual data and using ChatGPT to automatically generate the graph. We refine the results using filtering and mapping rules to align with our schema. The manually generated graph serves as the ground truth for evaluation, and we explore different methods to enhance its accuracy through knowledge graph completion techniques. As a result, we emphasize the potential of employing ChatGPT for automated knowledge graph construction within the Chinese medical domain. While ChatGPT successfully identifies a larger number of entities, further enhancements are required to improve its performance in extracting more qualified relations.

Nanjing Yunjin intelligent question-answering system based on knowledge graphs and retrieval augmented generation technology

Nanjing Yunjin, a traditional Chinese silk weaving craft, is celebrated globally for its unique local characteristics and exquisite workmanship, forming an integral part of the world's intangible cultural heritage. However, with the advancement of information technology, the experiential knowledge of the Nanjing Yunjin production process is predominantly stored in text format. As a highly specialized and vertical domain, this information is not readily convert into usable data. Previous studies on a knowledge graph-based Nanjing Yunjin Question-Answering System have partially addressed this issue. However, knowledge graphs need to be constantly updated and rely on predefined entities and relationship types. Faced with ambiguous or complex natural language problems, knowledge graph information retrieval faces some challenges. Therefore, this study proposes a Nanjing Yunjin Question-Answering System that integrates Knowledge Graphs and Retrieval Augmented Generation techniques. In this system, the ROBERTA model is first utilized to vectorize Nanjing Yunjin textual information, delving deep into textual semantics to unveil its profound cultural connotations. Additionally, the FAISS vector database is employed for efficient storage and retrieval of Nanjing Yunjin information, achieving a deep semantic match between questions and answers. Ultimately, related retrieval results are fed into the Large Language Model for enhanced generation, aiming for more accurate text generation outcomes and improving the interpretability and logic of the Question-Answering System. This research merges technologies like text embedding, vectorized retrieval, and natural language generation, aiming to overcome the limitations of knowledge graphs-based Question-Answering System in terms of graph updating, dependency on predefined types, and semantic understanding. System implementation and testing have shown that the Nanjing Yunjin Intelligent Question-Answering System, constructed on the basis of Knowledge Graphs and Retrieval Augmented Generation, possesses a broader knowledge base that considers context, resolving issues of polysemy, vague language, and sentence ambiguity, and efficiently and accurately generates answers to natural language queries. This significantly facilitates the retrieval and utilization of Yunjin knowledge, providing a paradigm for constructing Question-Answering System for other intangible cultural heritages, and holds substantial theoretical and practical significance for the deep exploration and discovery of the knowledge structure of human intangible heritage, promoting cultural inheritance and protection.

Implementation of Knowledge Management in Universities of India

This article examines the essential need for and difficulties related with the adoption of knowledge management (KM) strategies in institutions across India. The implementation of information Management, a methodical strategy for acquiring, arranging, and distributing institutional information, is becoming more and more crucial in the swiftly changing environment of higher education. The essay explores the specific circumstances of Indian universities, where a variety of academic fields, cultural subtleties, and administrative intricacies provide particular obstacles to the efficient administration of information. The use of Knowledge Management (KM) at Indian institutions is examined in relation to worldwide patterns and the revolutionary influence it may have on academic and administrative procedures. The paper emphasizes the possible advantages, such as increased cooperation, better decision-making, and optimized resource allocation. It also acknowledges the need for a cultural transformation inside academic institutions to promote a culture of sharing information among academics, students, and administrative personnel. Moreover, the study analyses the necessary technology infrastructure for effectively implementing knowledge management in Indian institutions. The text highlights the significance of using sophisticated information systems, cloud computing, and data analytics to enable effective generation, storage, and retrieval of knowledge. The significance of leadership in spearheading this cultural and technical transformation is underscored, as successful knowledge management requires robust institutional backing and strategic foresight. The article discusses the obstacles that arise while adopting Knowledge Management (KM) at Indian universities and business schools, including opposition to change, concerns over data security, and the need for capacity training. The article suggests implementing a gradual and flexible strategy, customized to the specific attributes of each university, to address these obstacles and optimize the advantages of knowledge management in promoting the academic objectives and overall efficiency of higher education institutions in India.

Knowledge Management System For Forest and Land Fire Mitigation in Indonesia: A Web-Based Application Development

Forest and land fires in Indonesia have serious impacts on many aspects, including the environment, health, economy, politics, and international relations. They cause haze pollution that extends to neighboring countries and peatland degradation. Despite extensive research and mitigation efforts, forest and land fires continue to occur and cost lives. Therefore, effective management and mitigation strategies are required. This research developed a web-based knowledge management system (KMS) using the Laravel framework as an effective forest and land fire mitigation platform. The KMS aims to support decision-making, facilitate knowledge exchange, improve coordination between stakeholders, and expand access to relevant information, while maintaining the sustainability of forest and land resources in Indonesia. The KMS evaluation results cover two important aspects: blackbox evaluation and performance evaluation. The blackbox evaluation showed that KMS provides knowledge retrieval features based on expert knowledge. The performance evaluation revealed that the KMS provides easy and quick access to information on forest and land fire prevention and management. Thus, this research has great potential to help overcome the problem of forest and land fires in Indonesia and protect the environment and society from their adverse effects.

What drives the automatic retrieval of real-world object size knowledge?

Real-world object size is a behaviorally relevant object property that is automatically retrieved when viewing object images: participants are faster to indicate the bigger of two object images when this object is also bigger in the real world. What drives this size Stroop effect? One possibility is that it reflects the automatic retrieval of real-world size after objects are recognized at the basic level (e.g., recognizing an object as a plane activates large real-world size). An alternative possibility is that the size Stroop effect is driven by automatic associations between low-/mid-level visual features (e.g., rectilinearity) and real-world size, bypassing object recognition. Here, we tested both accounts. In Experiment 1, objects were displayed upright and inverted, slowing down recognition while equating visual features. Inversion strongly reduced the Stroop effect, indicating that object recognition contributed to the Stroop effect. Independently of inversion, however, trial-wise differences in rectilinearity also contributed to the Stroop effect. In Experiment 2, the Stroop effect was compared between manmade objects (for which rectilinearity was associated with size) and animals (no association between rectilinearity and size). The Stroop effect was larger for animals than for manmade objects, indicating that rectilinear feature differences were not necessary for the Stroop effect. Finally, in Experiment 3, unrecognizable "texform" objects that maintained size-related visual feature differences were displayed upright and inverted. Results revealed a small Stroop effect for both upright and inverted conditions. Altogether, these results indicate that the size Stroop effect partly follows object recognition with an additional contribution from visual feature associations. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Semantic Technologies in Knowledge Management

Purpose: The general objective of this study was to explore semantic technologies in knowledge management.
 Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library.
 Findings: The findings reveal that there exists a contextual and methodological gap relating to semantic technologies in knowledge management. Preliminary empirical review revealed that these technologies hold significant potential for enhancing knowledge organization, retrieval, and utilization within organizations. While theoretical benefits were recognized, practical implementation faced challenges such as technical constraints, organizational resistance, and the need for alignment with organizational objectives. Despite these hurdles, the study emphasized the importance of overcoming barriers through comprehensive approaches involving technological solutions, organizational change management, and stakeholder engagement. Overall, the study highlighted the transformative potential of semantic technologies in knowledge management but underscored the necessity of addressing challenges to realize their full benefits.
 Unique Contribution to Theory, Practice and Policy: The Social Construction of Technology (SCOT) theory, Actor-Network Theory (ANT) and Resource-Based View (RBV) theory may be used to anchor future studies on semantic technologies. The study made several recommendations to enhance the adoption and utilization of semantic technologies. It suggested developing standardized ontologies, prioritizing user-centric design principles, and providing ongoing training to improve digital literacy among practitioners. Additionally, the study emphasized the importance of governance mechanisms for ensuring data quality, fostering collaborative networks for knowledge sharing, and embracing a culture of experimentation and adaptation. These recommendations aimed to address challenges such as interoperability, usability, and trustworthiness, ultimately enabling organizations to leverage semantic technologies more effectively in their knowledge management practices.

CyclicPepedia: a knowledge base of natural and synthetic cyclic peptides.

Cyclic peptides offer a range of notable advantages, including potent antibacterial properties, high binding affinity and specificity to target molecules, and minimal toxicity, making them highly promising candidates for drug development. However, a comprehensive database that consolidates both synthetically derived and naturally occurring cyclic peptides is conspicuously absent. To address this void, we introduce CyclicPepedia (https://www.biosino.org/iMAC/cyclicpepedia/), a pioneering database that encompasses 8744 known cyclic peptides. This repository, structured as a composite knowledge network, offers a wealth of information encompassing various aspects of cyclic peptides, such as cyclic peptides' sources, categorizations, structural characteristics, pharmacokinetic profiles, physicochemical properties, patented drug applications, and a collection of crucial publications. Supported by a user-friendly knowledge retrieval system and calculation tools specifically designed for cyclic peptides, CyclicPepedia will be able to facilitate advancements in cyclic peptide drug development.

Generative Multi-Modal Knowledge Retrieval with Large Language Models

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when it comes to training and integrating multiple retrievers to handle multi-modal queries. In this paper, we propose an innovative end-to-end generative framework for multi-modal knowledge retrieval. Our framework takes advantage of the fact that large language models (LLMs) can effectively serve as virtual knowledge bases, even when trained with limited data. We retrieve knowledge via a two-step process: 1) generating knowledge clues related to the queries, and 2) obtaining the relevant document by searching databases using the knowledge clue. In particular, we first introduce an object-aware prefix-tuning technique to guide multi-grained visual learning. Then, we align multi-grained visual features into the textual feature space of the LLM, employing the LLM to capture cross-modal interactions. Subsequently, we construct instruction data with a unified format for model training. Finally, we propose the knowledge-guided generation strategy to impose prior constraints in the decoding steps, thereby promoting the generation of distinctive knowledge clues. Through experiments conducted on three benchmarks, we demonstrate significant improvements ranging from 3.0% to 14.6% across all evaluation metrics when compared to strong baselines.

From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue

Retrieving appropriate records from the external knowledge base to generate informative responses is the core capability of end-to-end task-oriented dialogue systems (EToDs). Most of the existing methods additionally train the retrieval model or use the memory network to retrieve the knowledge base, which decouples the knowledge retrieval task from the response generation task, making it difficult to jointly optimize and failing to capture the internal relationship between the two tasks. In this paper, we propose a simple and unified generative model for task-oriented dialogue systems, which recasts the EToDs task as a single sequence generation task and uses maximum likelihood training to train the two tasks in a unified manner. To prevent the generation of non-existent records, we design the prefix trie to constrain the model generation, which ensures consistency between the generated records and the existing records in the knowledge base. Experimental results on three public benchmark datasets demonstrate that our method achieves robust performance on generating system responses and outperforms the baseline systems. To facilitate future research in this area, the code is available at https://github.com/dzy1011/Uni-ToD.

Automated Category and Trend Analysis of Scientific Articles on Ophthalmology Using Large Language Models: Development and Usability Study.

In this paper, we present an automated method for article classification, leveraging the power of large language models (LLMs). The aim of this study is to evaluate the applicability of various LLMs based on textual content of scientific ophthalmology papers. We developed a model based on natural language processing techniques, including advanced LLMs, to process and analyze the textual content of scientific papers. Specifically, we used zero-shot learning LLMs and compared Bidirectional and Auto-Regressive Transformers (BART) and its variants with Bidirectional Encoder Representations from Transformers (BERT) and its variants, such as distilBERT, SciBERT, PubmedBERT, and BioBERT. To evaluate the LLMs, we compiled a data set (retinal diseases [RenD] ) of 1000 ocular disease-related articles, which were expertly annotated by a panel of 6 specialists into 19 distinct categories. In addition to the classification of articles, we also performed analysis on different classified groups to find the patterns and trends in the field. The classification results demonstrate the effectiveness of LLMs in categorizing a large number of ophthalmology papers without human intervention. The model achieved a mean accuracy of 0.86 and a mean F1-score of 0.85 based on the RenD data set. The proposed framework achieves notable improvements in both accuracy and efficiency. Its application in the domain of ophthalmology showcases its potential for knowledge organization and retrieval. We performed a trend analysis that enables researchers and clinicians to easily categorize and retrieve relevant papers, saving time and effort in literature review and information gathering as well as identification of emerging scientific trends within different disciplines. Moreover, the extendibility of the model to other scientific fields broadens its impact in facilitating research and trend analysis across diverse disciplines.

Abstract 7659: AI-driven hypothesis-free analysis for biomarker discovery: Introducing the Biomarkers Navigator Framework

Abstract The pivotal role of biomarkers in personalizing patient treatment and guiding drug development is well-recognized, with the ultimate goal of enhancing therapeutic efficacy and patient quality of life by minimizing adverse events. Their development, however, is challenged by strict regulations and high costs, leading to sparse and varied data collected over extended periods and through diverse technologies. These variations complicate the harmonization and analysis of the data. Traditional methods struggle to navigate these complexities, further obscuring biomarker identification. For instance, PDL-1, approved as a biomarker by the FDA, has its effectiveness debated in several studies. To address these issues, we introduce Biomarkers Navigator, a flexible and automated analysis framework engineered explicitly for the robust identification of biomarkers. This framework is designed to aggregate, standardize, and store expansive biomarker information, ensuring efficient and traceable knowledge retrieval. By pre-calculating each potential biomarker, Biomarkers Navigator enables immediate and comprehensive meta-analyses, facilitating rapid decision-making tailored to the level of risk acceptance. Large Language Models (LLMs) further enhance the framework's capability to uncover signatures of response and resistance. LLM integration has accelerated the discovery of new potential biomarkers for hematological malignancies by combining prior knowledge and previously obscured associations. Our approach demonstrates the feasibility of large-scale hypothesis-free analysis and substantiates the utility of AI in unveiling hidden biological connections within clinical data. Our findings underscore the potential of AI-augmented frameworks in revolutionizing biomarker discovery and advancing personalized medicine. Citation Format: Ioannis Kagiampakis, Mishka Gidwani, Iaroslav Korkodinov, Georgiy Ponomarev, Etai Jacob. AI-driven hypothesis-free analysis for biomarker discovery: Introducing the Biomarkers Navigator Framework [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7659.

A field-based knowledge graph assisted conceptual design for structure configuration of engineering equipment

In the era of digital transformation, engineering design presents new development prospects. The key to conceptual design of engineering equipment lies in optimising structure configuration and effectively utilising knowledge support. Existing research focuses on the guidance of design methods to design activities and the auxiliary reasoning of knowledge systems, but ignores the close connection between knowledge systems and design activities. How to establish a coupling mechanism between knowledge systems and design activities to improve the accuracy of knowledge reasoning for structure configuration is the current challenge. Knowledge Graph (KG) has the advantages of structured organisation of heterogeneous knowledge and efficient knowledge retrieval. A framework for using field-based knowledge graph-assisted conceptual design (Field-KGCD) to support structure configuration of engineering equipment is proposed. Triples of structural entities and their interaction relationship are extracted from patent documents by event extraction technology. Energy sources related to structure interactions are used to establish the association relationships between different structure entities. Knowledge retrieval and recommendation strategy based on graph algorithm is proposed to achieve accurate knowledge assistance in the design process. A case study on the conceptual design of engineering drilling equipment demonstrates the feasibility of the proposed approach.

A knowledge graph-based bio-inspired design approach for knowledge retrieval and reasoning

Bio-inspired Design (BID) is a method that draws principles from biological systems to solve complex real-world problems. While diverse knowledge-based tools have served BID, the retrieval and reasoning capabilities of knowledge graphs have not been explored in BID. This study introduces a novel knowledge graph-based BID approach, exploiting the power of knowledge graphs to support BID. In the approach, a comprehensive ontology is defined and then applied to construct a BID-specific knowledge graph, enabling efficient representation of the diverse and rich biological knowledge. The knowledge graph supports BID by facilitating knowledge retrieval and reasoning. Retrieval in BID is accomplished by finding potential links between biological systems and relevant design applications. Reasoning in BID is supported by a link prediction model that follows the design process of mapping from biological systems to design applications. Two case studies are conducted to demonstrate the effectiveness of the approach. The first case shows that our approach outperforms other benchmarks in retrieving related biological knowledge, and the second case presents how the link prediction model aids in generating relevant and inspirational design ideas.

Generative Environment-Representation Instance-Based Learning: A Cognitive Model

Instance-Based Learning Theory (IBLT) suggests that humans learn to engage in dynamic decision making tasks through the accumulation of experiences, represented by the decision task features, the actions performed, and the utility of decision outcomes. This theory has been applied to the design of Instance-Based Learning (IBL) models of human behavior in a variety of contexts. One key feature of all IBL model applications is the method of accumulating instance-based memory and performing recognition-based retrieval. In simple tasks with few features, this knowledge representation and retrieval could hypothetically be done using all relevant information. However, these methods do not scale well to complex tasks when exhaustive enumeration of features is unfeasible. This requires cognitive modelers to design task-specific representations of state features, as well as similarity metrics, which can be time consuming and fail to generalize to related tasks. To address this issue, we leverage recent advancements in Artificial Neural Networks, specifically generative models (GMs), to learn representations of complex dynamic decision making tasks without relying on domain knowledge. We evaluate a range of GMs in their usefulness in forming representations that can be used by IBL models to predict human behavior in a complex decision making task. This work connects generative and cognitive models by using GMs to form representations and determine similarity.

Knowledge Repositories for Managing Knowledge in Learning Organizations

Learning organizations create a phenomenal amount of scholarly knowledge as part of their academic discourse and research activities. This scholarly knowledge must be preserved and made accessible to other members. The absence of tools and strategies to facilitate the storage and accessibility of knowledge and information resources poses lots of challenges for the growth of learning organizations, particularly, learning organizations in Ghana. This study, therefore, sought to assess the deployment of knowledge repositories in learning organizations toward effective knowledge creation, use, sharing, retention, and retrieval. The study employed the triangulation design and online survey research. The triangulation helped in the collection of quantitative data followed by qualitative instruments (interviews) to find answers to pertinent questions and issues that were insufficiently addressed in the questionnaire responses. Nine (9) learning organizations in Ghana participated in this study. The study established that knowledge repositories and technology played critical roles in managing knowledge in learning organizations. However, the knowledge repositories were not user-friendly and fully utilized or accessible for knowledge management practices at the learning organizations. Also, the absence of fully integrated ICT Tools and Infrastructure inhibited the effective promotion of knowledge management initiatives at the learning organizations. The study concludes by developing a knowledge repository architecture for knowledge management in learning organizations.

MechGPT, a Language-Based Strategy for Mechanics and Materials Modeling That Connects Knowledge Across Scales, Disciplines, and Modalities

Abstract For centuries, researchers have sought out ways to connect disparate areas of knowledge. While early scholars (Galileo, da Vinci, etc.) were experts across fields, specialization took hold later. With the advent of Artificial Intelligence, we can now explore relationships across areas (e.g., mechanics-biology) or disparate domains (e.g., failure mechanics-art). To achieve this, we use a fine-tuned large language model (LLM), here for a subset of knowledge in multiscale materials failure. The approach includes the use of a general-purpose LLM to distill question-answer pairs from raw sources followed by LLM fine-tuning. The resulting MechGPT LLM foundation model is used in a series of computational experiments to explore its capacity for knowledge retrieval, various language tasks, hypothesis generation, and connecting knowledge across disparate areas. While the model has some ability to recall knowledge from training, we find that LLMs are particularly useful for extracting structural insights through Ontological Knowledge Graphs. These interpretable graph structures provide explanatory insights, frameworks for new research questions, and visual representations of knowledge that also can be used in retrieval-augmented generation. Three versions of MechGPT are discussed, featuring different sizes from 13 × 109 to 70 × 109 parameters, and reaching context lengths of more than 10,000 tokens. This provides ample capacity for sophisticated retrieval augmented strategies, as well as agent-based modeling where multiple LLMs interact collaboratively and/or adversarially, the incorporation of new data from the literature or web searches, as well as multimodality.

Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection.

Video anomaly detection aims to find the events in a video that do not conform to the expected behavior. The prevalent methods mainly detect anomalies by snippet reconstruction or future frame prediction error. However, the error is highly dependent on the local context of the current snippet and lacks the understanding of normality. To address this issue, we propose to detect anomalous events not only by the local context, but also according to the consistency between the testing event and the knowledge about normality from the training data. Concretely, we propose a novel two-stream framework based on context recovery and knowledge retrieval, where the two streams can complement each other. For the context recovery stream, we propose a spatiotemporal U-Net which can fully utilize the motion information to predict the future frame. Furthermore, we propose a maximum local error mechanism to alleviate the problem of large recovery errors caused by complex foreground objects. For the knowledge retrieval stream, we propose an improved learnable locality-sensitive hashing, which optimizes hash functions via a Siamese network and a mutual difference loss. The knowledge about normality is encoded and stored in hash tables, and the distance between the testing event and the knowledge representation is used to reveal the probability of anomaly. Finally, we fuse the anomaly scores from the two streams to detect anomalies. Extensive experiments demonstrate the effectiveness and complementarity of the two streams, whereby the proposed two-stream framework achieves state-of-the-art performance on ShanghaiTech, Avenue and Corridor datasets among the methods without object detection. Even if compared with the methods using object detection, our method reaches competitive or better performance on the ShanghaiTech, Avenue, and Ped2 datasets.

Applied logic and semantics on indoor and urban adaptive design through knowledge graphs, reasoning and explainable argumentation

Abstract In the previous two decades, knowledge graphs (KGs) have evolved significantly, inspiring developers to build ever-more context-related KGs. Due to this development, artificial intelligence (AI) applications can now access open domain-specific information in a format that is both semantically rich and machine comprehensible. In this article, a framework that depicts functional design for indoor workspaces and urban adaptive design, in order to help architects, artists, and interior designers for the design and construction of an urban or indoor workspace, based on the emotions of human individuals, is introduced. For the creation of online adaptive environments, the framework may incorporate emotional, physiological, visual, and textual measures. Additionally, an information retrieval mechanism that extracts critical information from the framework in order to assist the architects, artists, and the interior designers is presented. The framework provides access to commonsense knowledge about the (re-)design of an urban area and an indoor workspace, by suggesting objects that need to be placed, and other modifications that can be applied to the location, in order to achieve positive emotions. The emotions referred reflect to the emotions experienced by an individual when being in the indoor or urban area, which are pointers for the functionality, the memorability, and the admiration of the location. The framework also performs semantic matching between entities from the web KG ConceptNet, using semantic knowledge from ConceptNet and WordNet, with the ones existing in the KG of the framework. The paper provides a set of predefined SPARQL templates that specifically handle the ontology upon which the knowledge retrieval system is based. The framework has an additional argumentation function that allows users to challenge the knowledge retrieval component findings. In the event that the user prevails in the reasoning, the framework will learn new knowledge.

Transformer networks of human conceptual knowledge.

We present a computational model capable of simulating aspects of human knowledge for thousands of real-world concepts. Our approach involves a pretrained transformer network that is further fine-tuned on large data sets of participant-generated feature norms. We show that such a model can successfully extrapolate from its training data, and predict human knowledge for new concepts and features. We apply our model to stimuli from 25 previous experiments in semantic cognition research and show that it reproduces many findings on semantic verification, concept typicality, feature distribution, and semantic similarity. We also compare our model against several variants, and by doing so, establish the model properties that are necessary for good prediction. The success of our approach shows how a combination of language data and (laboratory-based) psychological data can be used to build models with rich world knowledge. Such models can be used in the service of new psychological applications, such as the modeling of naturalistic semantic verification and knowledge retrieval, as well as the modeling of real-world categorization, decision-making, and reasoning. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Knowledge graph revision in the context of unknown knowledge.

The role of knowledge graph encompasses the representation, organization, retrieval, reasoning, and application of knowledge, providing a rich and robust cognitive foundation for artificial intelligence systems and applications. When we learn new things, find out that some old information was wrong, see changes and progress happening, and adopt new technology standards, we need to update knowledge graphs. However, in some environments, the initial knowledge cannot be known. For example, we cannot have access to the full code of a software, even if we purchased it. In such circumstances, is there a way to update a knowledge graph without prior knowledge? In this paper, We are investigating whether there is a method for this situation within the framework of Dalal revision operators. We first proved that finding the optimal solution in this environment is a strongly NP-complete problem. For this purpose, we proposed two algorithms: Flaccid_search and Tight_search, which have different conditions, and we have proved that both algorithms can find the desired results.