Synthesis of Programs from Multimodal Datasets
Authors: Shantanu Thakoor, Simoni Shah, Ganesh Ramakrishnan, Amitabha Sanyal
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our evaluations reflect the effectiveness of our approach. |
| Researcher Affiliation | Academia | Shantanu Thakoor Stanford University Stanford, CA 94305 thakoor@cs.stanford.edu Simoni Shah IIT Bombay Mumbai, 400076, India simonisamirshah@gmail.com Ganesh Ramakrishnan IIT Bombay Mumbai, 400076, India ganesh@cse.iitb.ac.in Amitabha Sanyal IIT Bombay Mumbai, 400076, India tas@cse.iitb.ac.in |
| Pseudocode | No | The paper describes algorithm steps in prose but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about open-sourcing code or a link to a code repository for the described methodology. |
| Open Datasets | Yes | We performed experiments on the settings described in the Co NLL reordering task (Khapra and Ramanathan 2012). |
| Dataset Splits | Yes | Under each scenario, tuning (used for learning f w) and test data of sizes 300 and 100 examples respectively, are simulated. |
| Hardware Specification | No | The paper mentions 'machines with a variety of configurations' but does not specify any particular CPU/GPU models, memory, or other detailed hardware specifications used for its experiments. |
| Software Dependencies | No | The paper mentions software like 'Alchemy2' and standard parsers, but does not provide specific version numbers for any key software components or libraries. |
| Experiment Setup | No | The paper mentions the use of a cutting-plane algorithm for Rank SVM and discusses feature weights, but does not provide specific hyperparameter values or detailed training configurations (e.g., learning rate, batch size, number of epochs) for the Multi Synth framework. |