Research map / Detection and segmentation / CNN features
Rich Event Modeling for Script Event Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use rich event descriptions with verb senses, extra semantic roles, and participant types | REP · MCNC-rich | accuracy: 54.33 -> 60.08 | Helped |
| add verb senses rather than using verb lemmas (ablation) | REP · MCNC-rich | accuracy: 59.28 -> 60.08 | Helped |
| add participant types (ablation) | REP · MCNC-rich | accuracy: 57.30 -> 60.08 | Helped |
| add extra semantic roles beyond ARG0, ARG1, and ARG2 (ablation) | REP · MCNC-rich | accuracy: 57.07 -> 60.08 | Helped |
| use the transformer-based rich event encoder instead of the fusion encoder (ablation) | REP · MCNC-rich | accuracy: 58.97 -> 60.08 | Helped |
| allow multiple participants with the same core semantic role | REP(F,-RT) · MCNC-rich | accuracy: 54.33 -> 55.97 | Helped |
| add participant types (ablation) | REP(F) · MCNC-rich | accuracy: 56.08 -> 58.97 | Helped |
| add participant types (ablation) | REP(-RT) · MCNC-rich | accuracy: 55.97 -> 57.07 | Helped |
| use the transformer-based rich event encoder instead of the fusion encoder, without participant types (ablation) | REP(-T) · MCNC-rich | accuracy: 56.08 -> 57.30 | Helped |
| use REP's event encoder with the existing event description | REP* · MCNC | accuracy: 59.24 -> 59.60 | Helped |
Closest papers by meaning
- A Generative Approach for Script Event Prediction via Contrastive Fine-Tuning (AAAI 2023 · similarity 0.90)
- SAM-Net: Integrating Event-Level and Chain-Level Attentions to Predict What Happens Next (AAAI 2019 · similarity 0.88)
- FEEL: Featured Event Embedding Learning (AAAI 2018 · similarity 0.88)
- Event Representations With Tensor-Based Compositions (AAAI 2018 · similarity 0.87)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.85)
- Selecting Optimal Context Sentences for Event-Event Relation Extraction (AAAI 2022 · 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.