Related papers: Improving the recall of decentralised linked data …
Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever…
There is a wide gap between symbolic reasoning and deep learning. In this research, we explore the possibility of using deep learning to improve symbolic reasoning. Briefly, in a reasoning system, a deep feedforward neural network is used…
In this paper, we propose a new approach for fast processing of SPARQL queries on large RDF datasets containing RDF quadruples (or quads). Our approach called RIQ employs a decrease-and-conquer strategy: Rather than indexing the entire RDF…
Reinforcement learning (RL) policies deployed in safety-critical systems, such as unmanned aerial vehicle (UAV) navigation in dynamic airspace, are vulnerable to out-ofdistribution (OOD) adversarial attacks in the observation space. These…
The W3C Web Ontology Language (OWL) is a powerful knowledge representation formalism at the basis of many semantic-centric applications. Since its unrestricted usage makes reasoning undecidable already in case of very simple tasks,…
Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on brittle formal logic. However, progress in this direction has…
The Resource Description Framework (RDF) is a W3C standard for representing graph-structured data, and SPARQL is the standard query language for RDF. Recent advances in Information Extraction, Linked Data Management and the Semantic Web…
Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…
Providing appropriate questions according to a student's knowledge level is imperative in personalized learning. However, It requires a lot of manual effort for teachers to understand students' knowledge status and provide optimal questions…
Natural language question-answering over RDF data has received widespread attention. Although there have been several studies that have dealt with a small number of aggregate queries, they have many restrictions (i.e., interactive…
The Web of Data has been gaining momentum and this leads to increasingly publish more semi-structured datasets following the RDF model, based on atomic triple units of subject, predicate, and object. Although it is a simple model,…
Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour. The second step has been widely studied in the…
Large language models (LLMs) have achieved remarkable performance on knowledge graph question answering (KGQA) tasks by planning and interacting with knowledge graphs. However, existing methods often confuse tool utilization with knowledge…
Retrieval-augmented generation (RAG) has emerged as a paradigm for grounding large language models in external knowledge, yet most existing RAG systems assume centralized knowledge access and ample computation. These assumptions break down…
Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process. However, the application of pseudo…
The SPARQL query language is a recent W3C standard for processing RDF data, a format that has been developed to encode information in a machine-readable way. We investigate the foundations of SPARQL query optimization and (a) provide novel…
The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge…
RDF data in the linked open data (LOD) cloud is very valuable for many different applications. In order to unlock the full value of this data, users should be able to issue complex queries on the RDF datasets in the LOD cloud. SPARQL can…
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two…
Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…