Research map / Graph learning / Knowledge and temporal graphs
Story Ending Generation with Multi-Level Graph Convolutional Networks over Dependency Trees
Qingbao Huang, Linzhang Mo, Pijian Li, Yi Cai, Qingguang Liu, Jielong Wei, Qing Li, Ho-fung Leung
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 |
|---|---|---|---|
| Add dependency parsing to the graph encoder (ablation) | MGCN-DP · ROCStories test | B1 (%): 22.0 -> 24.6 | Improved |
| Add multi-level information delivery (ablation) | MGCN-DP · ROCStories test | B1 (%): 21.7 -> 24.6 | Improved |
| Add dependency parsing and multi-level information delivery (ablation) | MGCN-DP · ROCStories test | Logic: 1.70 -> 1.86 | Improved |
| Add nsubj dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.7 -> 24.6 | Improved |
| Add dobj dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.7 -> 24.6 | Improved |
| Add acl dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.7 -> 24.6 | Improved |
| Add iobj dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.8 -> 24.6 | Improved |
| Add dep dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.8 -> 24.6 | Improved |
| Add amod dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.8 -> 24.6 | Improved |
| Add case dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.9 -> 24.6 | Improved |
| Add advmod dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 23.9 -> 24.6 | Improved |
| Add det dependency edges (ablation) | MGCN-DP · ROCStories test | B1 (%): 24.0 -> 24.6 | Improved |
Closest papers by meaning
- Discriminative Sentence Modeling for Story Ending Prediction (AAAI 2020 · similarity 0.86)
- Show Me a Story: Towards Coherent Neural Story Illustration (CVPR 2018 · similarity 0.84)
- Storytelling from an Image Stream Using Scene Graphs (AAAI 2020 · similarity 0.84)
- Story Ending Generation with Incremental Encoding and Commonsense Knowledge (AAAI 2019 · similarity 0.84)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.82)
- Dependency Structure-Enhanced Graph Attention Networks for Event Detection (AAAI 2024 · similarity 0.82)
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.
