Research map / Graph learning / Knowledge and temporal graphs
Incorporating Structured Commonsense Knowledge in Story Completion
Jiaao Chen, Jianshu Chen, Zhou Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Encode all five story sentences together rather than encoding body and ending separately (ablation) | Our Model · ROCStories test set | accuracy (%): 78.4 -> 87.6 | Improved |
| Add sentiment evolution to narrative sequence information (ablation) | Our Model · ROCStories test set | accuracy (%): 85.3 -> 87.6 | Improved |
| Add commonsense knowledge to narrative sequence information (ablation) | Our Model · ROCStories test set | accuracy (%): 85.3 -> 87.2 | Improved |
| Remove narrative sequence information (ablation) | Our Model (All Types) · ROCStories test set | accuracy (%): 87.6 -> 65.9 | Hurt |
| Remove sentiment evolution information (ablation) | Our Model (All Types) · ROCStories test set | accuracy (%): 87.6 -> 87.2 | Hurt |
| Remove commonsense knowledge (ablation) | Our Model (All Types) · ROCStories test set | accuracy (%): 87.6 -> 85.6 | Hurt |
| Use sentiment information alone instead of combining information sources (ablation) | Our Model · ROCStories test set | accuracy (%): 87.6 -> 58.7 | Hurt |
| Use commonsense knowledge alone instead of combining information sources (ablation) | Our Model · ROCStories test set | accuracy (%): 87.6 -> 63.8 | Hurt |
Closest papers by meaning
- Story Ending Generation with Incremental Encoding and Commonsense Knowledge (AAAI 2019 · similarity 0.90)
- Discriminative Sentence Modeling for Story Ending Prediction (AAAI 2020 · similarity 0.89)
- Paragraph-level Commonsense Transformers with Recurrent Memory (AAAI 2021 · similarity 0.86)
- M-sense: Modeling Narrative Structure in Short Personal Narratives Using Protagonist’s Mental Representations (AAAI 2023 · similarity 0.85)
- What Happens Next? Event Prediction Using a Compositional Neural Network Model (AAAI 2016 · similarity 0.85)
- Story Realization: Expanding Plot Events into Sentences (AAAI 2020 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
