Unsupervised Selection of Negative Examples for Grounded Language Learning
Authors: Nisha Pillai, Cynthia Matuszek
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our approach on a new data set of objects and descriptions, and our initial results support the idea that purely linguistic tools can be used to overcome weaknesses in corpora of perceptual training data. |
| Researcher Affiliation | Academia | Nisha Pillai, Cynthia Matuszek npillai1 | cmat @ umbc.edu Department of Computer Science and Electrical Engineering University of Maryland, Baltimore County Baltimore, Maryland |
| Pseudocode | No | The paper describes the system's processes in narrative text and figures but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | Our data set contains 72 objects, divided into 18 classes... To obtain descriptive language, the RGB images were posted on Amazon Mechanical Turk, and users provided short descriptions. The paper describes a new dataset collected for this work but does not provide access information (link, citation, or repository) for it. |
| Dataset Splits | Yes | Cross-validation was used for testing. |
| Hardware Specification | No | The paper mentions a 'Kinect2 camera' for data collection, but it does not specify any hardware details (e.g., GPU, CPU models, or memory) used for running the experiments or training the models. |
| Software Dependencies | No | The paper mentions algorithms like tf-idf, Paragraph Vector, and logistic regression but does not provide specific version numbers for any software libraries, frameworks, or dependencies used in the implementation. |
| Experiment Setup | Yes | Training is performed using logistic regression. |