Automated Storytelling via Causal, Commonsense Plot Ordering

Authors: Prithviraj Ammanabrolu, Wesley Cheung, William Broniec, Mark O. Riedl5859-5867

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Using human-participant protocols, we evaluate our system against baseline systems with different commonsense reasoning approaches and inductive biases to determine the role of soft causal relations in perceived story quality. Through these studies we also probe the interplay of how changes in commonsense norms across storytelling genres affect perceptions of story quality.
Researcher Affiliation Academia Prithviraj Ammanabrolu, Wesley Cheung, William Broniec, and Mark O. Riedl Georgia Institute of Technology {raj.ammanabrolu,wcheung8,d.tu,wbroniec3,riedl}@gatech.edu
Pseudocode No The paper describes the system architecture and processes with text and figures, but it does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Code found at https://github.com/rajammanabrolu/C2PO.
Open Datasets Yes We evaluate on a story dataset with two genres mystery stories and fairy tales first introduced by Ammanabrolu et al. (2020a)3. Footnote 3: https://github.com/rajammanabrolu/World Generation
Dataset Splits No The paper states: “The data is partitioned into train and test splits in a 8:2 ratio” but does not explicitly mention a separate validation set split or its details.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions several software tools and models like BERT, COMET, fairseq, and Open IE, but it does not provide specific version numbers for these software components or any other libraries like Python, PyTorch, or TensorFlow versions, which are needed to replicate the experiment.
Experiment Setup No The paper describes the overall experimental design, the human evaluation setup, and the statistical tests performed. However, it does not provide specific numerical hyperparameters (e.g., learning rate, batch size, number of epochs) or detailed training configurations for the models used in the experiments.