Solving Semantic Problems Using Contexts Extracted from Knowledge Graphs

Authors: Adrian Boteanu

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We implemented our topic modeling approach in two projects. The first uses an interactive story tablet application, Tinkr Book... In the second application, we use topics to predict ratings over the Yelp Academic Dataset. We are evaluating the analogy solving system on SAT questions.
Researcher Affiliation Academia Adrian Boteanu aboteanu@wpi.edu Worcester Polytechnic Institute
Pseudocode No No pseudocode or algorithm blocks are present in the paper.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes For our work, we choose a freely available knowledge base which meets this criteria, Concept Net (Havasi, Speer, and Alonso 2007)... In the second application, we use topics to predict ratings over the Yelp Academic Dataset.
Dataset Splits No The paper does not provide specific details on training, validation, and test dataset splits, such as percentages, sample counts, or explicit splitting methodologies.
Hardware Specification No No specific hardware details (e.g., CPU, GPU models, or memory) used for experiments are mentioned in the paper.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup No The paper does not contain specific experimental setup details such as hyperparameter values, training configurations, or system-level settings.