Generalized chart constraints for efficient PCFG and TAG parsing
This work addresses efficiency issues in natural language processing for parsing tasks, offering a significant speedup for researchers and practitioners, though it is incremental as it builds on existing chart constraint methods.
The authors tackled the problem of speeding up parsing for more expressive grammar formalisms by generalizing chart constraints and using a neural tagger to predict them with high precision, resulting in a two orders of magnitude speedup while improving accuracy.
Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs. We generalize chart constraints to more expressive grammar formalisms and describe a neural tagger which predicts chart constraints at very high precision. Our constraints accelerate both PCFG and TAG parsing, and combine effectively with other pruning techniques (coarse-to-fine and supertagging) for an overall speedup of two orders of magnitude, while improving accuracy.