Journal of Web Semantics最新文献_第3页

Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective 知识图谱、大型语言模型和幻觉：一个NLP的视角

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-12-24 DOI: 10.1016/j.websem.2024.100844

Ernests Lavrinovics , Russa Biswas , Johannes Bjerva , Katja Hose

{"title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","authors":"Ernests Lavrinovics , Russa Biswas , Johannes Bjerva , Katja Hose","doi":"10.1016/j.websem.2024.100844","DOIUrl":"10.1016/j.websem.2024.100844","url":null,"abstract":"<div><div>Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) based applications including automated text generation, question answering, chatbots, and others. However, they face a significant challenge: hallucinations, where models produce plausible-sounding but factually incorrect responses. This undermines trust and limits the applicability of LLMs in different domains. Knowledge Graphs (KGs), on the other hand, provide a structured collection of interconnected facts represented as entities (nodes) and their relationships (edges). In recent research, KGs have been leveraged to provide context that can fill gaps in an LLM’s understanding of certain topics offering a promising approach to mitigate hallucinations in LLMs, enhancing their reliability and accuracy while benefiting from their wide applicability. Nonetheless, it is still a very active area of research with various unresolved open problems. In this paper, we discuss these open challenges covering state-of-the-art datasets and benchmarks as well as methods for knowledge integration and evaluating hallucinations. In our discussion, we consider the current use of KGs in LLM systems and identify future directions within each of these challenges.</div></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"85 ","pages":"Article 100844"},"PeriodicalIF":2.1,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Serendipitous knowledge discovery on the Web of Wisdom based on searching and explaining interesting relations in knowledge graphs 基于搜索和解释知识图中有趣关系的智慧网上的偶然知识发现

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-12-24 DOI: 10.1016/j.websem.2024.100852

Eero Hyvönen

{"title":"Serendipitous knowledge discovery on the Web of Wisdom based on searching and explaining interesting relations in knowledge graphs","authors":"Eero Hyvönen","doi":"10.1016/j.websem.2024.100852","DOIUrl":"10.1016/j.websem.2024.100852","url":null,"abstract":"<div><div>This paper maintains that the Semantic Web is changing into a kind of Web of Wisdom (WoW) where AI-based problem solving, based on symbolic search and sub-symbolic methods, and Information Retrieval (IR) merge: IR is seen as a process for solving information-related problems of the end user with explanations, a form of knowledge discovery. As a case of example, relational search is concerned, i.e., solving problems of the type “How are <span><math><mrow><msub><mrow><mi>X</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>…</mo><msub><mrow><mi>X</mi></mrow><mrow><mi>n</mi></mrow></msub></mrow></math></span> related to <span><math><mrow><msub><mrow><mi>Y</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>…</mo><msub><mrow><mi>Y</mi></mrow><mrow><mi>m</mi></mrow></msub></mrow></math></span>?”. For example: how is <em>Pablo Picasso</em> related to <em>Barcelona</em>? The idea is to find explainable “interesting” or even serendipitous associations in Knowledge Graphs (KG) and textual web contents. It is argued that domain knowledge-based symbolic methods based of KGs are needed to complement domain-agnostic graph-based methods and Generative AI (GenAI) boosted by Large Language Models (LLM). By using domain specific knowledge, it is possible to find and explain meaningful reliable textual answers, answer quantitative questions, and use data analyses and visualizations for explaining and studying the relations.</div></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"85 ","pages":"Article 100852"},"PeriodicalIF":2.1,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

KG.GOV: Knowledge graphs as the backbone of data governance in AI 公斤。GOV：知识图谱是人工智能数据治理的支柱

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-12-20 DOI: 10.1016/j.websem.2024.100847

Albert Meroño-Peñuela, Elena Simperl, Anelia Kurteva, Ioannis Reklos

{"title":"KG.GOV: Knowledge graphs as the backbone of data governance in AI","authors":"Albert Meroño-Peñuela, Elena Simperl, Anelia Kurteva, Ioannis Reklos","doi":"10.1016/j.websem.2024.100847","DOIUrl":"10.1016/j.websem.2024.100847","url":null,"abstract":"<div><div>As (generative) Artificial Intelligence continues to evolve, so do the challenges associated with governing the data that powers it. Ensuring data quality, privacy, security, and ethical use become more and more challenging due to the increasing volume and variety of the data, the complexity of AI models, and the rapid pace of technological advancement. Knowledge graphs have the potential to play a significant role in enabling data governance in AI, as we move beyond their traditional use as data organisational systems. To address this, we present <span>KG.gov</span>, a framework that positions KGs at a higher abstraction level within AI workflows, and enables them as a backbone of AI data governance. We illustrate the three dimensions of <span>KG.gov</span>: modelling data, alternative representations, and describing behaviour; and describe the insights and challenges of three use cases implementing them: Croissant, a vocabulary to model and document ML datasets; WikiPrompts, a collaborative KG of prompts and prompt workflows to study their behaviour at scale; and Multimodal transformations, an approach for multimodal KGs harmonisation and completion aiming at broadening access to knowledge.</div></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"85 ","pages":"Article 100847"},"PeriodicalIF":2.1,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143165537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Editorial for the Special Issue on Knowledge Engineering 《知识工程》特刊社论

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-12-01 DOI: 10.1016/j.websem.2024.100840

Paul Groth , Eva Blomqvist , Juan F. Sequeda

引用次数: 0

Uniqorn: Unified question answering over RDF knowledge graphs and natural language text Uniqorn：通过 RDF 知识图谱和自然语言文本进行统一问题解答

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-09-10 DOI: 10.1016/j.websem.2024.100833

Soumajit Pramanik , Jesujoba Alabi , Rishiraj Saha Roy , Gerhard Weikum

{"title":"Uniqorn: Unified question answering over RDF knowledge graphs and natural language text","authors":"Soumajit Pramanik , Jesujoba Alabi , Rishiraj Saha Roy , Gerhard Weikum","doi":"10.1016/j.websem.2024.100833","DOIUrl":"10.1016/j.websem.2024.100833","url":null,"abstract":"<div><p>Question answering over RDF data like knowledge graphs has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries. Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone. Conversely, the IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for <em>complex questions</em> that can seamlessly operate over a mixture of RDF datasets and text corpora, or individual sources, in a unified framework. Our method, called <span>Uniqorn</span>, builds a context graph on-the-fly, by retrieving question-relevant evidences from the RDF data and/or a text corpus, using fine-tuned BERT models. The resulting graph typically contains all question-relevant evidences but also a lot of noise. <span>Uniqorn</span> copes with this input by a graph algorithm for Group Steiner Trees, that identifies the best answer candidates in the context graph. Experimental results on several benchmarks of complex questions with multiple entities and relations, show that <span>Uniqorn</span> significantly outperforms state-of-the-art methods for <em>heterogeneous QA</em> – in a full training mode, as well as in zero-shot settings. The graph-based methodology provides user-interpretable evidence for the complete answering process.</p></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"83 ","pages":"Article 100833"},"PeriodicalIF":2.1,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1570826824000192/pdfft?md5=1b3a7cdd704527ca28fe0609b32bbd44&pid=1-s2.0-S1570826824000192-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142238245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

KAE: A property-based method for knowledge graph alignment and extension KAE：基于属性的知识图谱排列和扩展方法

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-07-14 DOI: 10.1016/j.websem.2024.100832

Daqian Shi, Xiaoyue Li, Fausto Giunchiglia

{"title":"KAE: A property-based method for knowledge graph alignment and extension","authors":"Daqian Shi, Xiaoyue Li, Fausto Giunchiglia","doi":"10.1016/j.websem.2024.100832","DOIUrl":"10.1016/j.websem.2024.100832","url":null,"abstract":"<div><p>A common solution to the semantic heterogeneity problem is to perform knowledge graph (KG) extension exploiting the information encoded in one or more candidate KGs, where the alignment between the reference KG and candidate KGs is considered the critical procedure. However, existing KG alignment methods mainly rely on entity type (etype) label matching as a prerequisite, which is poorly performing in practice or not applicable in some cases. In this paper, we design a machine learning-based framework for KG extension, including an alternative novel property-based alignment approach that allows aligning etypes on the basis of the properties used to define them. The main intuition is that it is properties that intentionally define the etype, and this definition is independent of the specific label used to name an etype, and of the specific hierarchical schema of KGs. Compared with the state-of-the-art, the experimental results show the validity of the KG alignment approach and the superiority of the proposed KG extension framework, both quantitatively and qualitatively.</p></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"82 ","pages":"Article 100832"},"PeriodicalIF":2.1,"publicationDate":"2024-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1570826824000180/pdfft?md5=0e32d6cca795e8742e917608eef1c323&pid=1-s2.0-S1570826824000180-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141692104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-stream graph attention network for recommendation with knowledge graph 利用知识图谱进行推荐的多流图谱关注网络

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-06-29 DOI: 10.1016/j.websem.2024.100831

Zhifei Hu , Feng Xia

{"title":"Multi-stream graph attention network for recommendation with knowledge graph","authors":"Zhifei Hu , Feng Xia","doi":"10.1016/j.websem.2024.100831","DOIUrl":"10.1016/j.websem.2024.100831","url":null,"abstract":"<div><p>In recent years, the powerful modeling ability of Graph Neural Networks (GNNs) has led to their widespread use in knowledge-aware recommender systems. However, existing GNN-based methods for information propagation among entities in knowledge graphs (KGs) may not efficiently filter out less informative entities. To address this challenge and improve the encoding of high-order structure information among many entities, we propose an end-to-end neural network-based method called Multi-stream Graph Attention Network (MSGAT). MSGAT explicitly discriminates the importance of entities from four critical perspectives and recursively propagates neighbor embeddings to refine the target node. Specifically, we use an attention mechanism from the user's perspective to distill the domain nodes' information of the predicted item in the KG, enhance the user's information on items, and generate the feature representation of the predicted item. We also propose a multi-stream attention mechanism to aggregate user history click item's neighborhood entity information in the KG and generate the user's feature representation. We conduct extensive experiments on three real datasets for movies, music, and books, and the empirical results demonstrate that MSGAT outperforms current state-of-the-art baselines.</p></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"82 ","pages":"Article 100831"},"PeriodicalIF":2.1,"publicationDate":"2024-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1570826824000179/pdfft?md5=b3464b8bed3c0ac35eee561e19ca6a2a&pid=1-s2.0-S1570826824000179-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141960757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ontology design facilitating Wikibase integration — and a worked example for historical data 促进维基数据库整合的本体设计--历史数据实例

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-06-24 DOI: 10.1016/j.websem.2024.100823

Cogan Shimizu , Andrew Eells , Seila Gonzalez , Lu Zhou , Pascal Hitzler , Alicia Sheill , Catherine Foley , Dean Rehberger

引用次数: 0

Web3-DAO: An ontology for decentralized autonomous organizations Web3-DAO：分散自治组织本体论

IF 2.1 3区计算机科学

Journal of Web Semantics Pub Date : 2024-06-07 DOI: 10.1016/j.websem.2024.100830

María-Cruz Valiente, Juan Pavón

{"title":"Web3-DAO: An ontology for decentralized autonomous organizations","authors":"María-Cruz Valiente, Juan Pavón","doi":"10.1016/j.websem.2024.100830","DOIUrl":"10.1016/j.websem.2024.100830","url":null,"abstract":"<div><p>Decentralized autonomous organizations (DAOs) are relatively a newly emerging type of online entity related to governance or business models where all their members work together and participate in the decision-making processes affecting the DAO in a decentralized, collective, fair, and democratic manner. In a DAO, members interaction is mediated by software agents running on a blockchain that encode the governance of the specific entity in terms of rules that optimize their business and goals. In this context, most popular DAO software frameworks provide decision-making models aiming to facilitate digital governance and the collaboration among their members intertwining social and economic concerns. However, these models are complex, not interoperable among them and lack a common understanding and shared knowledge concerning DAOs, as well as the computational semantics needed to enable automated validation, simulation or execution. Thus, this paper presents an ontology (Web3-DAO), which can support machine-readable digital governance of DAOs adding semantics to their decision-making models. The proposed ontology captures the domain logic that allows the sharing of updated information and decisions for all the members that interact with a DAO by the interoperability of their own assessment and decision tools. Furthermore, the ontology detects semantic ambiguities, uncertainties and contradictions. The Web3-DAO ontology is available in open access at <span>https://github.com/Grasia/semantic-web3-dao</span><svg><path></path></svg>.</p></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"82 ","pages":"Article 100830"},"PeriodicalIF":2.1,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1570826824000167/pdfft?md5=50e4d4b40c93103a13362ae80c817a36&pid=1-s2.0-S1570826824000167-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141411685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving static and temporal knowledge graph embedding using affine transformations of entities 利用实体的仿射变换改进静态和时态知识图谱嵌入

IF 2.5 3区计算机科学

Journal of Web Semantics Pub Date : 2024-05-28 DOI: 10.1016/j.websem.2024.100824

Jinfa Yang, Xianghua Ying, Yongjie Shi, Ruibin Wang

{"title":"Improving static and temporal knowledge graph embedding using affine transformations of entities","authors":"Jinfa Yang, Xianghua Ying, Yongjie Shi, Ruibin Wang","doi":"10.1016/j.websem.2024.100824","DOIUrl":"https://doi.org/10.1016/j.websem.2024.100824","url":null,"abstract":"<div><p>To find a suitable embedding for a knowledge graph (KG) remains a big challenge nowadays. By measuring the distance or plausibility of triples and quadruples in static and temporal knowledge graphs, many reliable knowledge graph embedding (KGE) models are proposed. However, these classical models may not be able to represent and infer various relation patterns well, such as TransE cannot represent symmetric relations, DistMult cannot represent inverse relations, RotatE cannot represent multiple relations, <em>etc</em>.. In this paper, we improve the ability of these models to represent various relation patterns by introducing the affine transformation framework. Specifically, we first utilize a set of affine transformations related to each relation or timestamp to operate on entity vectors, and then these transformed vectors can be applied not only to static KGE models, but also to temporal KGE models. The main advantage of using affine transformations is their good geometry properties with interpretability. Our experimental results demonstrate that the proposed intuitive design with affine transformations provides a statistically significant increase in performance with adding a few extra processing steps and keeping the same number of embedding parameters. Taking TransE as an example, we employ the scale transformation (the special case of an affine transformation). Surprisingly, it even outperforms RotatE to some extent on various datasets. We also introduce affine transformations into RotatE, Distmult, ComplEx, TTransE and TComplEx respectively, and experiments demonstrate that affine transformations consistently and significantly improve the performance of state-of-the-art KGE models on both static and temporal knowledge graph benchmarks.</p></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"82 ","pages":"Article 100824"},"PeriodicalIF":2.5,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1570826824000106/pdfft?md5=c556da96eab16cdef47d1fff590e4a7d&pid=1-s2.0-S1570826824000106-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141324691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0