Ontology Instance Linking: Towards Interlinked Knowledge Graphs
Authors: Jeff Heflin, Dezhao Song
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this paper, we first summarize state-of-the-art algorithms in detecting such coreference relationships between ontology instances. We then discuss various techniques in scaling entity coreference to large-scale datasets. Finally, we present well-adopted evaluation datasets and metrics, and compare the performance of the state-of-the-art algorithms on such datasets. ... First of all, in Table 2, we compare the state-of-the-art algorithms on the Person-Restaurant datasets from OAEI ... In Table 3, we also compare the state-of-the-art blocking algorithms on 100K instances from RKB and SWAT. Furthermore, Table 4 shows the actual coreference results on 50K and 100K randomly selected instances from BTC. Finally, in Figure 1, we compare Dis NGram and Ed Join (the best blocking systems from Table 3 in terms of Fcs and T) on up to 2 million instances from BTC. |
| Researcher Affiliation | Collaboration | Jeff Heflin Department of Computer Science and Engineering Lehigh University 19 Memorial Drive West Bethlehem, PA 18015, USA Dezhao Song Research and Development Thomson Reuters 610 Opperman Drive Eagan, MN 55123, USA |
| Pseudocode | No | The paper describes various algorithms and techniques in prose but does not include any structured pseudocode or algorithm blocks (e.g., labeled 'Algorithm 1'). |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code for the methodologies described within the paper, nor does it include links to a code repository. |
| Open Datasets | Yes | First of all, the Ontology Alignment Evaluation Initiative (OAEI)11 includes an instance matching track from 2009 that provides several benchmark datasets. ... Furthermore, in our prior work, two datasets: RKB12 and SWAT13, were adopted; both datasets contain millions of instances... Finally, we introduce the Billion Triples Challenge (BTC) dataset. ... 11http://oaei.ontologymatching.org/ 12http://www.rkbexplorer.com/data/ 13http://swat.cse.lehigh.edu/resources/data/ |
| Dataset Splits | No | The paper discusses the datasets used for evaluation and their characteristics (e.g., synthetic vs. real-world, number of instances) but does not specify how these datasets were partitioned into training, validation, and test splits for the experiments presented in the results tables. |
| Hardware Specification | No | The paper describes various algorithms, datasets, and evaluation metrics related to ontology instance linking and scaling, but it does not provide any specific details regarding the hardware (e.g., CPU, GPU models, memory) used to conduct the experiments. |
| Software Dependencies | No | The paper mentions several systems and tools (e.g., Log Map, Ri MOM, SERIMI, EPWNG, Dis NGram) but does not list any specific software dependencies or their version numbers (e.g., programming languages, libraries, frameworks) required to reproduce the experiments. |
| Experiment Setup | No | The paper presents performance comparisons of various algorithms on different datasets and discusses factors influencing results (e.g., modifications in Person2 dataset). However, it does not provide specific details about the experimental setup, such as hyperparameters, training configurations, or system-level settings used for the algorithms evaluated. |