Programming by Example Using Least General Generalizations
Authors: Mohammad Raza, Sumit Gulwani, Natasa Milic-Frayling
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present experimental results on tasks collected from online help forums, showing an average of 4.17 examples required for task completion. |
| Researcher Affiliation | Industry | Mohammad Raza Microsoft Research Cambridge 21 Station Road, Cambridge, CB1 2FB, U.K. a-moraza@microsoft.com Sumit Gulwani Microsoft Research Redmond One Microsoft Way, Redmond, WA 98052-6399, U.S.A. sumitg@microsoft.com Natasa Milic-Frayling Microsoft Research Cambridge 21 Station Road, Cambridge, CB1 2FB, U.K. natasamf@microsoft.com |
| Pseudocode | Yes | Figure 4: Program synthesis algorithm |
| Open Source Code | No | No explicit statement providing open-source code or a repository link for the described methodology was found. |
| Open Datasets | No | The paper states: "We performed an evaluation of the system using examples from online help forums (http://www.msofficeforums.com, http://www.vbaexpress.com/forum)." and "Since actual documents associated with the tasks were not available in the forum questions, we chose them either from a collection of files from the internet or, if the task described a particular document structure, then we created a sample document based on that description". This indicates that task ideas were sourced from forums, and custom or found documents were used, but no specific public dataset with access information was provided for the experiments. |
| Dataset Splits | No | No specific details about training, validation, or test splits were provided, nor cross-validation setup. |
| Hardware Specification | No | No specific hardware (CPU, GPU, memory) or computational resources used for experiments were mentioned. |
| Software Dependencies | No | The paper mentions "Microsoft Power Point 2013" as the environment for their add-in but does not specify any development software, libraries, or versions for reproducibility. |
| Experiment Setup | No | No specific experimental setup details such as hyperparameters, learning rates, or training configurations were provided. The 'Experimental Evaluation' section describes the tasks and number of examples required, rather than configuration settings for model training. |