"Okay guys, if you want to read one article about ontologies, taxonomy, and data, this is the one. Congratulations Graham.

While LLMs have shown remarkable prowess in understanding and generating text, they have a critical limitation.

Despite the fact that it affects our lives on a daily basis, most of us are unfamiliar with the concept of a knowledge graph. When we ask Alexa about tomorrow's weather or use Google to look up the latest news on climate change, knowledge graphs serve as the foundation of today's cutting-edge information systems. In addition, knowledge graphs have the potential to elucidate, assess, and substantiate information produced by Deep Learning models, such as Chat-GPT and other large language models. Knowledge graphs have a wide range of applications, including improving search results, answering questions, providing recommendations, and developing explainable AI systems. In essence, the purpose of this course is to provide a comprehensive overview of knowledge graphs, their underlying technologies, and their significance in today's digital world.

The evidence for the massive impact of KGs in NLQ keeps piling up - Here's one more paper that shows that knowledge graph based RAG (retrieval-augmentation)…

We’re excited to announce a new AI-powered Skills in Viva service that will help organizations understand workforce skills and gaps, and deliver personalized skills-based experiences.

One of our main focuses at Zazuko GmbH is to support government organizations in publishing multidimensional data in RDF format. To this end, we utilize the cube.

This is the first of a series of blogs wherein I describe what we believe is a superior pattern for creating highly performant, real-world…

On August 14, 2023, the paper Natural Language is All a Graph Needs by Ruosong Ye, Caiqi Zhang, Runhui Wang, Shuyuan Xu and Yongfeng Zhang…

Knowledge graphs (KGs) comprise entities interconnected by relations of different semantic meanings. KGs are being used in a wide range of applications. However, they inherently suffer from incompleteness, i.e. entities or facts about entities are missing. Consequently, a larger body of works focuses on the completion of missing information in KGs, which is commonly referred to as link prediction (LP). This task has traditionally and extensively been studied in the transductive setting, where all entities and relations in the testing set are observed during training. Recently, several works have tackled the LP task under more challenging settings, where entities and relations in the test set may be unobserved during training, or appear in only a few facts. These works are known as inductive, few-shot, and zero-shot link prediction. In this work, we conduct a systematic review of existing works in this area. A thorough analysis leads us to point out the undesirable existence of diverging terminologies and task definitions for the aforementioned settings, which further limits the possibility of comparison between recent works. We consequently aim at dissecting each setting thoroughly, attempting to reveal its intrinsic characteristics. A unifying nomenclature is ultimately proposed to refer to each of them in a simple and consistent manner.

This week Alexander Erdl and I did our last #GoingMeta of the year, and we talked about Advanced #RAG patterns with #KnowledgeGraphs and vector search. We…

Large language models (LLMs), such as ChatGPT and LLaMA, are creating significant advancements in natural language processing, due to their strong text encoding/decoding ability and newly found emergent capability (e.g., reasoning). While LLMs are mainly designed to process pure texts, there are many real-world scenarios where text data are associated with rich structure information in the form of graphs (e.g., academic networks, and e-commerce networks) or scenarios where graph data are paired with rich textual information (e.g., molecules with descriptions). Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graph scenarios (i.e., graph-based reasoning). In this paper, we provide a systematic review of scenarios and techniques related to large language models on graphs. We first summarize potential scenarios of adopting LLMs on graphs into three categories, namely pure graphs, text-rich graphs, and text-paired graphs. We then discuss detailed techniques for utilizing LLMs on graphs, including LLM as Predictor, LLM as Encoder, and LLM as Aligner, and compare the advantages and disadvantages of different schools of models. Furthermore, we mention the real-world applications of such methods and summarize open-source codes and benchmark datasets. Finally, we conclude with potential future research directions in this fast-growing field. The related source can be found at https://github.com/PeterGriffinJin/Awesome-Language-Model-on-Graphs.

When reading lengthy or intricate texts, keeping an overview of different dependencies within the context is crucial. Traditionally, humans achieve this through note-taking or mentally creating a concept map. Now imagine having AI at hand which generates such a map for you. Even better, the…

Enhancing AI Accuracy: Telco Network Knowledge Graph's Role in Overcoming LLM Hallucinations LLMs are known to create responses that, while appearing valid…

The internals of a SHACL engine — how Ontotext GraphDB validates your data

Natural language interfaces to databases have long been a holy grail of both industry and academia. Recently, advances in large language…

I'm constantly looking for new ways to explain why and how knowledge graphs are important. A presentation this week led me to formulate a different, mathier… | 29 comments on LinkedIn

Prompting an LLM with an ontology to drive Knowledge Graph extraction from unstructured documents

Introduction

Extract hidden insights from unstructured data

This paper discusses the different roles that explicit knowledge, in particular ontologies, can play in Explainable AI and in the development of human-centric explainable systems and intelligible explanations. We consider three main perspectives in which ontologies can contribute significantly, namely reference modelling, common-sense reasoning, and knowledge refinement and complexity management. We overview some of the existing approaches in the literature, and we position them according to these three proposed perspectives. The paper concludes by discussing what challenges still need to be addressed to enable ontology-based approaches to explanation and to evaluate their human-understandability and effectiveness.

Knowledge graphs and ontologies, like any other mission-critical resource, require a laser-sharp focus on architecture, accuracy, and coverage. Essentially all downstream processes rely on them, as does the overall success of any knowledge-centric AI product or company.

I really enjoyed the latest #UnconfuseMe with Bill Gates and Yejin Choi.  Yejin's research is on symbolic knowledge distillation, which means they take large…

The advent of large language models (LLMs) , trained on vast amounts of text data, has been one of the most significant breakthroughs in…

Note: This article and the underlying LLM application were developed with Alexander Gilmore, Associate Consulting Engineer at Neo4j.

Knowledge Graph Construction (KGC) can be seen as an iterative process starting from a high quality nucleus that is refined by knowledge extraction approaches in a virtuous loop. Such a nucleus can be obtained from knowledge existing in an open KG like Wikidata. However, due to the size of such generic KGs, integrating them as a whole may entail irrelevant content and scalability issues. We propose an analogy-based approach that starts from seed entities of interest in a generic KG, and keeps or prunes their neighboring entities. We evaluate our approach on Wikidata through two manually labeled datasets that contain either domain-homogeneous or -heterogeneous seed entities. We empirically show that our analogy-based approach outperforms LSTM, Random Forest, SVM, and MLP, with a drastically lower number of parameters. We also evaluate its generalization potential in a transfer learning setting. These results advocate for the further integration of analogy-based inference in tasks related to the KG lifecycle.

Applying SHACL to your data and handling the output

Learn how SHACL can help you tame your unruly data graphs

The integration of heterogeneous and weakly linked log data poses a major challenge in many log-analytic applications. Knowledge graphs (KGs) can facilitate such integration by providing a versatile representation that can interlink objects of interest and enrich log events with background knowledge. Furthermore, graph-pattern based query languages, such as SPARQL, can support rich log analyses by leveraging semantic relationships between objects in heterogeneous log streams. Constructing, materializing, and maintaining centralized log knowledge graphs, however, poses significant challenges. To tackle this issue, we propose VloGraph—a distributed and virtualized alternative to centralized log knowledge graph construction. The proposed approach does not involve any a priori parsing, aggregation, and processing of log data, but dynamically constructs a virtual log KG from heterogeneous raw log sources across multiple hosts. To explore the feasibility of this approach, we developed a prototype and demonstrate its applicability to three scenarios. Furthermore, we evaluate the approach in various experimental settings with multiple heterogeneous log sources and machines; the encouraging results from this evaluation suggest that the approach can enable efficient graph-based ad-hoc log analyses in federated settings.

LLMs vs human understanding