Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction

2018/06/09 by Siyuan Qi, Baoxiong Jia, Qi, Siyuan +3 · 4 citations
Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1806.03497

openalex publication_date 2018/06/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Future predictions on sequence data (e.g., videos or audios) require the algorithms to capture non-Markovian and compositional properties of high-level semantics. Context-free grammars are natural choices to capture such properties, but traditional grammar parsers (e.g., Earley parser) only take symbolic sentences as inputs. In this paper, we generalize the Earley parser to parse sequence data which is neither segmented nor labeled. This generalized Earley parser integrates a grammar parser with a classifier to find the optimal segmentation and labels, and makes top-down future predictions. Experiments show that our method significantly outperforms other approaches for future human activity prediction.

Cited by

• Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• Interpretable Intuitive Physics Model
• ACRE: Abstract Causal REasoning Beyond Covariation

Related

• Grammatical Sequence Prediction for Real-Time Neural Semantic Parsing
• LATE Ain'T Earley: A Faster Parallel Earley Parser
• Structured Prediction of Sequences and Trees using Infinite Contexts
• A Probabilistic Generative Grammar for Semantic Parsing
• Robust stochastic parsing using the inside-outside algorithm