How to Keep a Knowledge Base Synchronized with Its Encyclopedia Source
Authors: Jiaqing Liang, Sheng Zhang, Yanghua Xiao
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct extensive experiments to justify the effectiveness of the proposed system, model, as well as the underlying principles. |
| Researcher Affiliation | Collaboration | Jiaqing Liang12, Sheng Zhang1, Yanghua Xiao134 1School of Computer Science, Shanghai Key Laboratory of Data Science Fudan University, Shanghai, China 2Shuyan Technology, Shanghai, China 3Shanghai Internet Big Data Engineering Technology Research Center, China 4Xiaoi Research, Shanghai, China |
| Pseudocode | Yes | Algorithm 1 USB: Update System for KB |
| Open Source Code | Yes | The code and data are available at http://kw.fudan.edu.cn/resources/data/bdupd.zip |
| Open Datasets | Yes | The update system was further deployed on our knowledge base CN-DBpedia1, which is created from the largest Chinese encyclopedia Baidu Baike2. ... We first collect the whole changing logs for 94k entities in Baidu Baike. |
| Dataset Splits | No | The paper states 'We randomly split our labeled 94K entities into training set (90%) and test set (10%)' but does not explicitly mention a separate validation split. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | We use the implementations in scikit-learn [Pedregosa et al., 2011]. Specifically, for the linear model, we use ridge linear regression, which uses linear least squares loss and l2 regularization. |
| Experiment Setup | No | The paper describes the features used and the models (linear regression, random forest) but does not provide specific hyperparameters such as learning rates, batch sizes, or regularization parameters for the experimental setup. |