Research map / Video / Video-language understanding
A Unified Bayesian Model of Scripts, Frames and Language
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 semantic frame and role levels (UPF) to the template model, observed only at training (ablation) | Template model on NYT articles · 1K held-out NYT documents | average held-out log-likelihood | Helped |
| add semantic frame and role levels (UPF), verb distributions with frames marginalized (ablation) | Template model on NYT articles · Topic coherence at M=20 | coherence | Helped |
Closest papers by meaning
- Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields (AAAI 2024 · similarity 0.83)
- TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation (ICML 2025 · similarity 0.83)
- Efficient semantic uncertainty quantification in language models via diversity-steered sampling (NeurIPS 2025 · similarity 0.83)
- Markovian Transformers for Informative Language Modeling (ICLR 2026 · similarity 0.83)
- Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning (NeurIPS 2024 · similarity 0.83)
- Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback (NeurIPS 2026 · 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.