SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graph

The recent success of Large Language Models (LLM) in a wide range of Natural Language Processing applications opens the path towards novel Question Answering Systems over Knowledge Graphs leveraging LLMs. However, one of the main obstacles preventing their implementation is the scarcity of training data for the task of translating questions into corresponding SPARQL queries, particularly in the case of domain-specific KGs. To overcome this challenge, in this study, we evaluate several strategies for fine-tuning the OpenLlama LLM for question answering over life science knowledge graphs. In particular, we propose an end-to-end data augmentation approach for extending a set of existing queries over a given knowledge graph towards a larger dataset of semantically enriched question-to-SPARQL query pairs, enabling fine-tuning even for datasets where these pairs are scarce. In this context, we also investigate the role of semantic "clues" in the queries, such as meaningful variable names and inline comments. Finally, we evaluate our approach over the real-world Bgee gene expression knowledge graph and we show that semantic clues can improve model performance by up to 33% compared to a baseline with random variable names and no comments included.

On the Potential of Artificial Intelligence Chatbots for Data Exploration of Federated Bioinformatics Knowledge Graphs

In this paper, we present work in progress on the role of artificial intelligence (AI) chatbots, such as ChatGPT, in facilitating data access to federated knowledge graphs. In particular, we provide examples from the field of bioinformatics, to illustrate the potential use of Conversational AI to describe datasets, as well as generate and explain (federated) queries across datasets for the benefit of domain experts.

INODE: Building an End-to-End Data Exploration System in Practice [Extended Vision]

A full-fledged data exploration system must combine different access modalities with a powerful concept of guiding the user in the exploration process, by being reactive and anticipative both for data discovery and for data linking. Such systems are a real opportunity for our community to cater to users with different domain and data science expertise. We introduce INODE -- an end-to-end data exploration system -- that leverages, on the one hand, Machine Learning and, on the other hand, semantics for the purpose of Data Management (DM). Our vision is to develop a classic unified, comprehensive platform that provides extensive access to open datasets, and we demonstrate it in three significant use cases in the fields of Cancer Biomarker Reearch, Research and Innovation Policy Making, and Astrophysics. INODE offers sustainable services in (a) data modeling and linking, (b) integrated query processing using natural language, (c) guidance, and (d) data exploration through visualization, thus facilitating the user in discovering new insights. We demonstrate that our system is uniquely accessible to a wide range of users from larger scientific communities to the public. Finally, we briefly illustrate how this work paves the way for new research opportunities in DM.

IfcWoD, Semantically Adapting IFC Model Relations into OWL Properties

In the context of Building Information Modelling, ontologies have been identified as interesting in achieving information interoperability. Regarding the construction and facility management domains, several IFC (Industry Foundation Classes) based ontologies have been developed, such as IfcOWL. In the context of ontology modelling, the constraint of optimizing the size of IFC STEP-based files can be leveraged. In this paper, we propose an adaptation of the IFC model into OWL which leverages from all modelling constraints required by the object-oriented structure of IFC schema. Therefore, we do not only present a syntactic but also a semantic adaptation of the IFC model. Our model takes into consideration the meaning of entities, relationships, properties and attributes defined by the IFC standard. Our approach presents several advantages compared to other initiatives such as the optimization of query execution time. Every advantage is defended by means of practical examples and benchmarks.