Research map / Label-efficient and robust learning / Recognition and long-tail
Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction
Siyuan Qi, Baoxiong Jia, Song-Chun Zhu
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 |
|---|---|---|---|
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · CAD-120 detection | Micro P/R: 76.2 -> 79.4 | Improved |
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · CAD-120 future 3s prediction | Micro P/R: 54.2 -> 61.5 | Improved |
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · CAD-120 segment prediction | Micro P/R: 31.4 -> 72.2 | Improved |
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · Watch-n-Patch detection | Micro P/R: 84.0 -> 84.8 | Improved |
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · Watch-n-Patch future 3s prediction | Micro P/R: 42.1 -> 49.0 | Improved |
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · Watch-n-Patch future 3s prediction | Macro F1-score: 61.8 -> 55.3 | Hurt |
| apply the generalized Earley parser to Bi-LSTM classifier outputs | Bi-LSTM · Watch-n-Patch segment prediction | Micro P/R: 21.7 -> 35.6 | Improved |
| use grammar-guided parsing instead of Bi-LSTM alone | CAD-120 and Watch-n-Patch future prediction · CAD-120 and Watch-n-Patch | future prediction accuracy | Mixed |
Closest papers by meaning
- A Generalized Earley Parser for Human Activity Parsing and Prediction (TPAMI 2020 · similarity 0.98)
- TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation (ICML 2025 · similarity 0.82)
- RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility (NeurIPS 2025 · similarity 0.82)
- Improving Unsupervised Constituency Parsing via Maximizing Semantic Information (ICLR 2025 · similarity 0.81)
- Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences (ICLR 2025 · similarity 0.81)
- Provable Length Generalization in Sequence Prediction via Spectral Filtering (ICML 2025 · similarity 0.81)
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.
