Tommaso Soru

Faisal Alshargi, Saeedeh Shekarpour, Tommaso Soru et al.

Although there is an emerging trend towards generating embeddings for primarily unstructured data and, recently, for structured data, no systematic suite for measuring the quality of embeddings has been proposed yet. This deficiency is further sensed with respect to embeddings generated for structured data because there are no concrete evaluation metrics measuring the quality of the encoded structure as well as semantic patterns in the embedding space. In this paper, we introduce a framework containing three distinct tasks concerned with the individual aspects of ontological concepts: (i) the categorization aspect, (ii) the hierarchical aspect, and (iii) the relational aspect. Then, in the scope of each task, a number of intrinsic metrics are proposed for evaluating the quality of the embeddings. Furthermore, w.r.t. this framework, multiple experimental studies were run to compare the quality of the available embedding models. Employing this framework in future research can reduce misjudgment and provide greater insight about quality comparisons of embeddings for ontological concepts. We positioned our sampled data and code at https://github.com/alshargi/Concept2vec under GNU General Public License v3.0.

Tommaso Soru, Jim Marshall

In the constantly changing field of data-driven decision making, accurately predicting future events is crucial for strategic planning in various sectors. The emergence of Large Language Models (LLMs) marks a significant advancement in this area, offering advanced tools that utilise extensive text data for prediction. In this industry paper, we introduce a novel method for AI-driven foresight using LLMs. Building on top of previous research, we employ data on current trends and their trajectories for generating forecasts on 15 different topics. Subsequently, we estimate their probabilities via a multi-step approach based on log probabilities. We show we achieve a Brier score of 0.186, meaning a +26% improvement over random chance and a +19% improvement over widely-available AI systems.

Abdulsobur Oyewale, Tommaso Soru

Enterprise Knowledge Graphs have become essential for unifying heterogeneous data and enforcing semantic governance. However, the construction of their underlying ontologies remains a resource-intensive, manual process that relies heavily on domain expertise. This paper introduces OntoEKG, a LLM-driven pipeline designed to accelerate the generation of domain-specific ontologies from unstructured enterprise data. Our approach decomposes the modelling task into two distinct phases: an extraction module that identifies core classes and properties, and an entailment module that logically structures these elements into a hierarchy before serialising them into standard RDF. Addressing the significant lack of comprehensive benchmarks for end-to-end ontology construction, we adopt a new evaluation dataset derived from documents across the Data, Finance, and Logistics sectors. Experimental results highlight both the potential and the challenges of this approach, achieving a fuzzy-match F1-score of 0.724 in the Data domain while revealing limitations in scope definition and hierarchical reasoning.

Anand Panchbhai, Tommaso Soru, Edgard Marx

A booming amount of information is continuously added to the Internet as structured and unstructured data, feeding knowledge bases such as DBpedia and Wikidata with billions of statements describing millions of entities. The aim of Question Answering systems is to allow lay users to access such data using natural language without needing to write formal queries. However, users often submit questions that are complex and require a certain level of abstraction and reasoning to decompose them into basic graph patterns. In this short paper, we explore the use of architectures based on Neural Machine Translation called Neural SPARQL Machines to learn pattern compositions. We show that sequence-to-sequence models are a viable and promising option to transform long utterances into complex SPARQL queries.

Tommaso Soru, Edgard Marx, André Valdestilhas et al.

We argue that "Question Answering with Knowledge Base" and "Question Answering over Linked Data" are currently two instances of the same problem, despite one explicitly declares to deal with Linked Data. We point out the lack of existing methods to evaluate question answering on datasets which exploit external links to the rest of the cloud or share common schema. To this end, we propose the creation of new evaluation settings to leverage the advantages of the Semantic Web to achieve AI-complete question answering.

Gustavo Correa Publio, Diego Esteves, Agnieszka Ławrynowicz et al.

The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is also mapped to other more domain-specific ontologies developed in the area of machine learning and data mining. In this paper we overview existing state-of-the-art machine learning interchange formats and present the first release of ML-Schema, a canonical format resulted of more than seven years of experience among different research institutions. We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability of experiments regardless of platform or adopted workflow solution.

Tommaso Soru, Edgard Marx, André Valdestilhas et al.

Research on question answering with knowledge base has recently seen an increasing use of deep architectures. In this extended abstract, we study the application of the neural machine translation paradigm for question parsing. We employ a sequence-to-sequence model to learn graph patterns in the SPARQL graph query language and their compositions. Instead of inducing the programs through question-answer pairs, we expect a semi-supervised approach, where alignments between questions and queries are built through templates. We argue that the coverage of language utterances can be expanded using late notable works in natural language generation.

Tommaso Soru, Stefano Ruberto, Diego Moussallem et al.

Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space. Several approaches using embeddings have shown promising results on tasks such as link prediction, entity recommendation, question answering, and triplet classification. However, only a few methods can compute low-dimensional embeddings of very large knowledge bases without needing state-of-the-art computational resources. In this paper, we propose KG2Vec, a simple and fast approach to Knowledge Graph Embedding based on the skip-gram model. Instead of using a predefined scoring function, we learn it relying on Long Short-Term Memories. We show that our embeddings achieve results comparable with the most scalable approaches on knowledge graph completion as well as on a new metric. Yet, KG2Vec can embed large graphs in lesser time by processing more than 250 million triples in less than 7 hours on common hardware.

Tommaso Soru, André Valdestilhas, Edgard Marx et al.

Graph representations of large knowledge bases may comprise billions of edges. Usually built upon human-generated ontologies, several knowledge bases do not feature declared ontological rules and are far from being complete. Current rule mining approaches rely on schemata or store the graph in-memory, which can be unfeasible for large graphs. In this paper, we introduce HornConcerto, an algorithm to discover Horn clauses in large graphs without the need of a schema. Using a standard fact-based confidence score, we can mine close Horn rules having an arbitrary body size. We show that our method can outperform existing approaches in terms of runtime and memory consumption and mine high-quality rules for the link prediction task, achieving state-of-the-art results on a widely-used benchmark. Moreover, we find that rules alone can perform inference significantly faster than embedding-based methods and achieve accuracies on link prediction comparable to resource-demanding approaches such as Markov Logic Networks.

Edgard Marx, Tommaso Soru, André Valdestilhas

With the continuous increase of data daily published in knowledge bases across the Web, one of the main issues is regarding information relevance. In most knowledge bases, a triple (i.e., a statement composed by subject, predicate, and object) can be only true or false. However, triples can be assigned a score to have information sorted by relevance. In this work, we describe the participation of the Catsear team in the Triple Scoring Challenge at the WSDM Cup 2017. The Catsear approach scores triples by combining the answers coming from three different sources using a linear regression classifier. We show how our approach achieved an Accuracy2 value of 79.58% and the overall 4th place.

Tommaso Soru, Diego Esteves, Edgard Marx et al.

Markov Logic Networks join probabilistic modeling with first-order logic and have been shown to integrate well with the Semantic Web foundations. While several approaches have been devised to tackle the subproblems of rule mining, grounding, and inference, no comprehensive workflow has been proposed so far. In this paper, we fill this gap by introducing a framework called Mandolin, which implements a workflow for knowledge discovery specifically on RDF datasets. Our framework imports knowledge from referenced graphs, creates similarity relationships among similar literals, and relies on state-of-the-art techniques for rule mining, grounding, and inference computation. We show that our best configuration scales well and achieves at least comparable results with respect to other statistical-relational-learning algorithms on link prediction.

Tommaso Soru, Edgard Marx, Diego Moussallem et al.

In the last years, the Linked Data Cloud has achieved a size of more than 100 billion facts pertaining to a multitude of domains. However, accessing this information has been significantly challenging for lay users. Approaches to problems such as Question Answering on Linked Data and Link Discovery have notably played a role in increasing information access. These approaches are often based on handcrafted and/or statistical models derived from data observation. Recently, Deep Learning architectures based on Neural Networks called seq2seq have shown to achieve state-of-the-art results at translating sequences into sequences. In this direction, we propose Neural SPARQL Machines, end-to-end deep architectures to translate any natural language expression into sentences encoding SPARQL queries. Our preliminary results, restricted on selected DBpedia classes, show that Neural SPARQL Machines are a promising approach for Question Answering on Linked Data, as they can deal with known problems such as vocabulary mismatch and perform graph pattern composition.