KELP: a Kernel-based Learning Platform
Authors: Simone Filice, Giuseppe Castellucci, Giovanni Da San Martino, Alessandro Moschitti, Danilo Croce, Roberto Basili
JMLR 2017 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Ke LP is a Java framework that enables fast and easy implementation of kernel functions over discrete data, such as strings, trees or graphs and their combination with standard vectorial kernels. Additionally, it provides several kernel-based algorithms, e.g., online and batch kernel machines for classification, regression and clustering, and a Java environment for easy implementation of new algorithms. ... The procedure for training and evaluating such classifier can be written in less than 20 code lines, as shown in Listing 1. ... evaluator.add Count(ex , classifier .predict(ex)); } System.out.println("ACC:" + evaluator. get Performance Measure ("accuracy")); |
| Researcher Affiliation | Collaboration | Simone Filice EMAIL DICII, University of Roma, Tor Vergata, Italy; Giovanni Da San Martino EMAIL Qatar Computing Research Institute, HKBU, Qatar; Alessandro Moschitti EMAIL Amazon |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. It provides a Java code listing (Listing 1) as an example of framework usage, which is not pseudocode. |
| Open Source Code | Yes | The Ke LP source code is distributed under the terms of Apache 2.0 License. No additional software is required to be installed in order to use it, the Apache Maven project management tool resolves all module dependencies automatically. We also provide and maintain a website with updated tutorials and documentation. |
| Open Datasets | No | The paper mentions data representations and formats (e.g., SVM-Light-TK input format, gspan format for graphs, Open Babel formats), and discusses how the framework can handle various data types. However, it does not provide concrete access information (links, DOIs, specific citations) for any datasets used in its own demonstrations or examples to allow for reproducibility. |
| Dataset Splits | No | The paper includes a code snippet (Listing 1) that shows 'Simple Dataset train Dataset' and 'Simple Dataset test Dataset' being populated. This implies the use of training and testing sets, but no specific details about how these splits are defined (e.g., percentages, sample counts, or methodology) are provided. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as CPU models, GPU models, or memory specifications used for running experiments. |
| Software Dependencies | No | The paper states that 'Ke LP is written in Java and uses three different Maven projects' and mentions 'the Apache Maven project management tool resolves all module dependencies automatically.' However, specific version numbers for Java or Maven are not provided. |
| Experiment Setup | Yes | Figure 1 provides 'A JSON description of a SVM classifier' which includes specific hyperparameter values such as 'c: 10', 'mu: 0.4', 'lambda: 0.4', and 'terminal Factor: 1.0'. |