Research map / Video / Video segmentation and tracking
What Happens Next? Future Subevent Prediction Using Contextual Hierarchical LSTM
Linmei Hu, Juanzi Li, Liqiang Nie, Xiao-Li Li, Chao Shao
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 topic (LDA) features to hierarchical LSTM (ablation) | HLSTM · Sina News subevent prediction, test | perplexity: 129.44 -> 127.74 | Improved |
| add topic (LDA) features to hierarchical LSTM (ablation) | HLSTM · Sina News subevent prediction, test | word error rate: 71.06% -> 70.02% | Improved |
| add topic (LDA) features to hierarchical LSTM (ablation) | HLSTM · Next subevent ranking | hits@1: 25.11% -> 25.79% | Improved |
| two-level hierarchical encoding instead of flat concatenated LSTM (ablation) | LSTM prediction model · Sina News subevent prediction, test | perplexity: 201.59 -> 129.44 | Improved |
| two-level hierarchical encoding instead of flat concatenated LSTM (ablation) | LSTM prediction model · Sina News subevent prediction, test | word error rate: 75.22% -> 71.06% | Improved |
| two-level hierarchical encoding instead of flat concatenated LSTM (ablation) | LSTM prediction model · Next subevent ranking | hits@1: 21.96% -> 25.11% | Improved |
| neural LSTM language model instead of 5-gram models | future subevent prediction · Sina News subevent prediction, test | perplexity: 255.48 -> 201.59 | Improved |
Closest papers by meaning
- Interacting Diffusion Processes for Event Sequence Forecasting (ICML 2024 · similarity 0.83)
- Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective (NeurIPS 2026 · similarity 0.83)
- Approaching Human-Level Forecasting with Language Models (NeurIPS 2024 · similarity 0.83)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.83)
- From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection (NeurIPS 2024 · similarity 0.82)
- Future Language Modeling from Temporal Document History (ICLR 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.
