Small language models (SLMs) have shown promises for relation extraction (RE) when extracting RDF triples guided by SHACL shapes focused on common datatype properties. This paper investigates how SLMs handle both datatype and object properties for a complete RDF graph extraction. We show that the key bottleneck is related to long-tail distribution of rare properties. To solve this issue, we evaluate several strategies: stratified sampling, weighted loss, dataset scaling, and template-based synthetic data augmentation. We show that the best strategy to perform equally well over unbalanced target properties is to build a training set where the number of occurrences of each property exceeds a given threshold. To enable reproducibility, we publicly released our datasets, experimental results and code. Our findings offer practical guidance for training shape-aware SLMs and highlight promising directions for future work in semantic RE.

RDF pattern-based extraction is a compelling approach for fine-tuning small language models (SLMs) by focusing a relation extraction task on a specified SHACL shape. This technique enables the development of efficient models trained on limited text and RDF data. In this article, we introduce Kastor, a framework that advances this approach to meet the demands for completing and refining knowledge bases in specialized domains. Kastor reformulates the traditional validation task, shifting from single SHACL shape validation to evaluating all possible combinations of properties derived from the shape. By selecting the optimal combination for each training example, the framework significantly enhances model generalization and performance. Additionally, Kastor employs an iterative learning process to refine noisy knowledge bases, enabling the creation of robust models capable of uncovering new, relevant facts.

Ontologies often lack explicit disjointness declarations between classes, despite their usefulness for sophisticated reasoning and consistency checking in Knowledge Graphs. In this study, we explore the potential of Large Language Models (LLMs) to enrich ontologies by identifying and asserting class disjointness axioms. Our approach aims at leveraging the implicit knowledge embedded in LLMs, using prompt engineering to elicit this knowledge for classifying ontological disjointness. We validate our methodology on the DBpedia ontology, focusing on open-source LLMs. Our findings suggest that LLMs, when guided by effective prompt strategies, can reliably identify disjoint class relationships, thus streamlining the process of ontology completion without extensive manual input. For comprehensive disjointness enrichment, we propose a process that takes logical relationships between disjointness and subclass statements into account in order to maintain satisfiability and reduce the number of calls to the LLM. This work provides a foundation for future applications of LLMs in automated ontology enhancement and offers insights into optimizing LLM performance through strategic prompt design. Our code is publicly available on GitHub at https://github.com/n28div/llm-disjointness.

This paper examines the capacity of LLMs to reason with knowledge graphs using their internal knowledge graph, i.e., the knowledge graph they learned during pre-training. Two research questions are formulated to investigate the accuracy of LLMs in recalling information from pre-training knowledge graphs and their ability to infer knowledge graph relations from context. To address these questions, we employ LLMs to perform four distinct knowledge graph reasoning tasks. Furthermore, we identify two types of hallucinations that may occur during knowledge reasoning with LLMs: content and ontology hallucination. Our experimental results demonstrate that LLMs can successfully tackle both simple and complex knowledge graph reasoning tasks from their own memory, as well as infer from input context.

Since ChatGPT offers detailed responses without justifications, and erroneous facts even for popular persons, events and places, in this paper we present a novel pipeline that retrieves the response of ChatGPT in RDF and tries to validate the ChatGPT facts using one or more RDF Knowledge Graphs (KGs). To this end we leverage DBpedia and LODsyndesis (an aggregated Knowledge Graph that contains 2 billion triples from 400 RDF KGs of many domains) and short sentence embeddings, and introduce an algorithm that returns the more relevant triple(s) accompanied by their provenance and a confidence score. This enables the validation of ChatGPT responses and their enrichment with justifications and provenance. To evaluate this service (such services in general), we create an evaluation benchmark that includes 2,000 ChatGPT facts; specifically 1,000 facts for famous Greek Persons, 500 facts for popular Greek Places, and 500 facts for Events related to Greece. The facts were manually labelled (approximately 73% of ChatGPT facts were correct and 27% of facts were erroneous). The results are promising; indicatively for the whole benchmark, we managed to verify the 85.3% of the correct facts of ChatGPT and to find the correct answer for the 58% of the erroneous ChatGPT facts.

Knowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). Learning versatile KGEs is desirable as it makes them useful for a broad range of tasks. However, KGEMs are usually trained for a specific task, which makes their embeddings task-dependent. In parallel, the widespread assumption that KGEMs actually create a semantic representation of the underlying entities and relations (e.g., project similar entities closer than dissimilar ones) has been challenged. In this work, we design heuristics for generating protographs -- small, modified versions of a KG that leverage RDF/S information. The learnt protograph-based embeddings are meant to encapsulate the semantics of a KG, and can be leveraged in learning KGEs that, in turn, also better capture semantics. Extensive experiments on various evaluation benchmarks demonstrate the soundness of this approach, which we call Modular and Agnostic SCHema-based Integration of protograph Embeddings (MASCHInE). In particular, MASCHInE helps produce more versatile KGEs that yield substantially better performance for entity clustering and node classification tasks. For link prediction, using MASCHinE substantially increases the number of semantically valid predictions with equivalent rank-based performance.

We recently proposed a new cluster operating system stack, DBOS, centered on a DBMS. DBOS enables unique support for ML applications by encapsulating ML code within stored procedures, centralizing ancillary ML data, providing security built into the underlying DBMS, co-locating ML code and data, and tracking data and workflow provenance. Here we demonstrate a subset of these benefits around two ML applications. We first show that image classification and object detection models using GPUs can be served as DBOS stored procedures with performance competitive to existing systems. We then present a 1D CNN trained to detect anomalies in HTTP requests on DBOS-backed web services, achieving SOTA results. We use this model to develop an interactive anomaly detection system and evaluate it through qualitative user feedback, demonstrating its usefulness as a proof of concept for future work to develop learned real-time security services on top of DBOS.

Knowledge graph embedding is a representation learning technique that projects entities and relations in a knowledge graph to continuous vector spaces. Embeddings have gained a lot of uptake and have been heavily used in link prediction and other downstream prediction tasks. Most approaches are evaluated on a single task or a single group of tasks to determine their overall performance. The evaluation is then assessed in terms of how well the embedding approach performs on the task at hand. Still, it is hardly evaluated (and often not even deeply understood) what information the embedding approaches are actually learning to represent. To fill this gap, we present the DLCC (Description Logic Class Constructors) benchmark, a resource to analyze embedding approaches in terms of which kinds of classes they can represent. Two gold standards are presented, one based on the real-world knowledge graph DBpedia and one synthetic gold standard. In addition, an evaluation framework is provided that implements an experiment protocol so that researchers can directly use the gold standard. To demonstrate the use of DLCC, we compare multiple embedding approaches using the gold standards. We find that many DL constructors on DBpedia are actually learned by recognizing different correlated patterns than those defined in the gold standard and that specific DL constructors, such as cardinality constraints, are particularly hard to be learned for most embedding approaches.

Most existing approaches for Knowledge Base Question Answering (KBQA) focus on a specific underlying knowledge base either because of inherent assumptions in the approach, or because evaluating it on a different knowledge base requires non-trivial changes. However, many popular knowledge bases share similarities in their underlying schemas that can be leveraged to facilitate generalization across knowledge bases. To achieve this generalization, we introduce a KBQA framework based on a 2-stage architecture that explicitly separates semantic parsing from the knowledge base interaction, facilitating transfer learning across datasets and knowledge graphs. We show that pretraining on datasets with a different underlying knowledge base can nevertheless provide significant performance gains and reduce sample complexity. Our approach achieves comparable or state-of-the-art performance for LC-QuAD (DBpedia), WebQSP (Freebase), SimpleQuestions (Wikidata) and MetaQA (Wikimovies-KG).

A particular question we are interested in answering is how well neural methods, and specifically transformer models, such as BERT, perform on the answer type prediction task compared to traditional approaches. Our main finding is that coarse-grained answer types can be identified effectively with standard text classification methods, with over 95% accuracy, and BERT can bring only marginal improvements. For fine-grained type detection, on the other hand, BERT clearly outperforms previous retrieval-based approaches.