1,720,968 research outputs found
Development of a high performance distributed computation system based on a cluster-grid
No full text
A term-based approach for matching multilingual thesauri
No full textIn this paper, we present a multilingual matching approach aiming at building matches between terms belonging to multilingual thesauri. The approach is presented as a variant of the schema matching problem and present its evaluation on domain-specific use cases by demonstrating the viability of the proposed technique for facing the multilingual thesaurus matching approach
BitsAndBites at SemEval-2025 Task 9: Improving Food Hazard Detection with Sequential Multitask Learning and Large Language Models
Full text linkAutomatic and early detection of foodborne hazards is crucial for preventing foodborne outbreaks. Existing AI-based solutions often cannot handle complexity and noise in food recall reports and they struggle to overcome the dependency between product and hazard labels. We introduce a methodology for classifying reports on food-related incidents that addresses these challenges. Our approach leverages LLM-based information extraction, to minimize report variability, along with a two-stage classification pipeline. The first model assigns coarse-grained labels that narrow the space of eligible fine-grained labels for the second model. This sequential process allows us to capture hierarchical label dependencies between products and hazards and between their respective categories. Additionally, we designed each model with two classification heads that rely on the inherent relations between food products and associated hazards. We validate our approach on two multi-label classification sub-tasks. Experimental results demonstrate the effectiveness of our approach, which achieves an improvement of +30% and +40% in classification performance compared to the baseline
Specifying Web Service Compositions on the Basis of Natural Language Requests
No full textThe introduction of the Semantic Web techniques in Service-oriented Architectures enables explicit representation and reasoning about semantically rich descriptions of service operations. Those techniques hold promise for the automated discovery, selection, composition and binding of services. This paper describes an approach to derive formal specifications of Web Service compositions on the basis of the interpretation of informal user requests expressed in (controlled) Natural Language. Our approach leverages the semantic and ontological description of a portfolio of known service operations (called Semantic Service Catalog
- …
