Best-first chart parsing utilises a figure of merit (FOM) to efficiently guide a parse by first attending to those edges judged better. In the past it has usually been static; this paper will show that with some extra information, a parser can compensate for FOM flaws which otherwise slow it down. Our results are faster than the prior best by a factor of 2.5; and the speedup is won with no significant decrease in parser accuracy.
@inproceedings{blah99,
author = {Don Blaheta and Eugene Charniak},
year = 1999,
title = {Automatic compensation for parser figure-of-merit flaws},
booktitle = {Proceedings of the 37th annual meeting of the
{A}ssociation for {C}omputational {L}inguistics},
pages = {513--518} }
Other papers