Using Social Relationships to Control Narrative Generation

Authors: Julie Porteous, Fred Charles, Marc Cavazza

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Narrative Diversity Results of experiments reported in (Porteous, Charles, and Cavazza 2013), obtained across hundreds of runs of the system measured in terms of real-time performance and story diversity, demonstrate the potential for the approach to yield large differences between generated stories via moderate changes to the social network.
Researcher Affiliation Academia Julie Porteous and Fred Charles and Marc Cavazza School of Computing, Teesside University Middlesbrough, United Kingdom {j.porteous,f.charles,m.o.cavazza}@tees.ac.uk
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the described methodology.
Open Datasets No The paper describes its own domain model ('the NETWORKING domain model has a cast of 10 doctors, 5 nurses, 3 patients and close to 100 narrative actions') but does not provide concrete access information (link, DOI, formal citation for public access) for a publicly available or open dataset.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts, or citations to predefined splits) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper describes the system architecture and domain model, but it does not contain specific experimental setup details such as concrete hyperparameter values or training configurations.