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.
@article{arxiv.1806.10654,
title = {Generalized chart constraints for efficient PCFG and TAG parsing},
author = {Stefan Grünewald and Sophie Henning and Alexander Koller},
journal= {arXiv preprint arXiv:1806.10654},
year = {2018}
}