Minimizing User Involvement for Accurate Ontology Matching Problems

Authors: Anika Schumann, Freddy Lecue

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that our approach can be successfully applied to real-world data sets. The paper concludes with an experimental evaluation. We therefore evaluated our approach for two use cases for which we had access to the correct matching as verified by a domain expert. The results are shown in Figure 5.
Researcher Affiliation Industry Anika Schumann and Freddy Lécué IBM Research Ireland Damastown Industrial Estate, Dublin, Ireland {(firstname.lastname)@ie.ibm.com}
Pseudocode Yes Procedure 1 Get V alidated OMR(G, z) 1: RUI Get Elem(M) // required user inputs 2: U // user input set 3: while not(RUI U) do 4: M Get Ontology Matching Result(G, U) 5: RUI Get Max SATsol(MURP(G, M, z), U) 6: u Get Elem In(M) // user input 7: while (M |= u) and not(RUI U) do 8: r Get Element(RUI \ U) 9: u Get User Input(r) 10: U U u 11: return M
Open Source Code No The paper does not provide any explicit statements or links indicating that its source code is open-source or publicly available.
Open Datasets No The paper describes using real-world data from a commercial building (2,239 descriptions) and transportation loop detector data from Dublin and Bologna. However, it does not provide concrete access information (links, DOIs, repositories, or formal citations with access details) for these datasets, nor does it refer to them as publicly available or open in a way that allows direct access.
Dataset Splits No The paper does not provide specific details about training, validation, or test dataset splits (e.g., percentages, sample counts, or explicit splitting methodologies).
Hardware Specification Yes Experiments were run on a Linux Dual-Core PC with 2GB of RAM.
Software Dependencies No The paper mentions "Pseudo-Boolean max SAT solver Mini SAT+ (Een and Sorensson 2006)" and "CEL DL reasoner (http://lat.inf.tudresden.de/systems/cel/)". While specific tools are named, explicit version numbers (e.g., Mini SAT+ vX.Y, CEL DL reasoner vZ.W) are not provided in the text.
Experiment Setup No The paper details characteristics of the problem instances (e.g., 2,239 descriptions, 1,317 matchings, 20,033 clauses and 382 variables for computing the minimum user request set), but it does not specify typical experimental setup parameters such as hyperparameters (e.g., learning rate, batch size, epochs) or specific training configurations for a model.