Content-Structural Relation Inference in Knowledge Base
Authors: Zeya Zhao, Yantao Jia, Yuanzhuo Wang
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on data sets show that CSRI obtains 15% improvement compared with the state-of-the-art methods. |
| Researcher Affiliation | Academia | 1CAS Key lab of Network Data Science & Technology, Institute of Computing Technology , CAS, Beijing, 100190, China 2National Digital Switching System Engineering and Technological Research Center, Zhengzhou, P. R. China |
| Pseudocode | No | The paper describes the steps of CSRI in paragraph text, but it does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | The experiments are carried out via cross-validation on two public data sets, Freebase and Wikipedia. |
| Dataset Splits | No | The paper mentions 'cross-validation' and 'remove 20% of their relations in the KB' for evaluation, but does not provide specific train/validation/test dataset splits (exact percentages or sample counts for each of the three) to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | By observation, we find that when , ( ) 0.01 s t P A and , ( ) 0.99 s t P P the performance of CSRI obtains the best. |