Research map / Label-efficient and robust learning / Recognition and long-tail
FEEL: Featured Event Embedding Learning
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 |
|---|---|---|---|
| add argument information (subject, object, prep) to event embedding objective (ablation) | FEEL PredDep · MCNC test | accuracy: 0.4232 -> 0.5135 | Helped |
| add animacy feature (ablation) | FEEL PredDep+Args · MCNC test | accuracy: 0.5135 -> 0.5503 | Helped |
| add sentiment feature (ablation) | FEEL PredDep+Args · MCNC test | accuracy: 0.5135 -> 0.5166 | Helped |
| add sentiment on top of animacy (use both features) (ablation) | FEEL PredDep+Args+A · MCNC test | accuracy: 0.5503 -> 0.5418 | Hurt |
| add sentiment feature to GloVe+PredDep+Args (ablation) | GloVe+FEEL · MCNS | accuracy (Viterbi): 0.332 -> 0.416 | Helped |
| use both sentiment and animacy instead of one (ablation) | GloVe+FEEL · MCNS | accuracy (Viterbi): 0.416 -> 0.365 | Hurt |
| add sentiment feature (ablation) | GloVe+PredDep+Args · MCNE | accuracy (Viterbi): 0.37 -> 0.448 | Helped |
| use both sentiment and animacy instead of sentiment alone (ablation) | GloVe+FEEL · MCNE | accuracy (Viterbi): 0.448 -> 0.403 | Hurt |
| concatenate FEEL embeddings with GloVe | GloVe · SICK | Pearson: 0.7102 -> 0.7676 | Helped |
| add sentiment feature (ablation) | GloVe+FEEL PredDep+Args · SICK | Pearson: 0.7572 -> 0.7518 | No clear effect |
| add animacy feature (ablation) | GloVe+FEEL PredDep+Args · SICK | Pearson: 0.7572 -> 0.7676 | Helped |
| add FEEL embeddings (all features) to GloVe | GloVe · CoNLL 2016 IDSC test | micro F1: 0.2982 -> 0.3174 | Helped |
Closest papers by meaning
- A Generative Approach for Script Event Prediction via Contrastive Fine-Tuning (AAAI 2023 · similarity 0.89)
- What Happens Next? Event Prediction Using a Compositional Neural Network Model (AAAI 2016 · similarity 0.88)
- Rich Event Modeling for Script Event Prediction (AAAI 2023 · similarity 0.88)
- NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative (ICLR 2025 · similarity 0.84)
- EventLens: Event-Structure Reinforcement Learning for Video Understanding (NeurIPS 2026 · similarity 0.84)
- E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024 · similarity 0.83)
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.