Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction
This work addresses the challenge of capturing non-Markovian and compositional semantics in sequence data for applications such as activity prediction, representing an incremental advancement by adapting a symbolic parser to real-world data.
The paper tackles the problem of future prediction on sequence data like videos or audios by generalizing the Earley parser to handle unsegmented and unlabeled sequences, integrating it with a classifier for optimal segmentation and labels, and achieving significant performance improvements over other methods in human activity prediction.
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.