tailieunhanh - Báo cáo khoa học: "Efficient, Feature-based, Conditional Random Field Parsing"

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data. | Efficient Feature-based Conditional Random Field Parsing Jenny Rose Finkel Alex Kleeman Christopher D. Manning Department of Computer Science Stanford University Stanford CA 94305 jrfinkel@ akleeman@ manning@ Abstract Discriminative feature-based methods are widely used in natural language processing but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences we present the first general featurerich discriminative parser based on a conditional random field model which has been successfully scaled to the full WSJ parsing data. Our efficiency is primarily due to the use of stochastic optimization techniques as well as parallelization and chart prefiltering. On WSJ15 we attain a state-of-the-art F-score of a 14 relative reduction in error over previous models while being two orders of magnitude faster. On sentences of length 40 our system achieves an F-score of a 36 relative reduction in error over a generative baseline. 1 Introduction Over the past decade feature-based discriminative models have become the tool of choice for many natural language processing tasks. Although they take much longer to train than generative models they typically produce higher performing systems in large part due to the ability to incorporate arbitrary potentially overlapping features. However constituency parsing remains an area dominated by generative methods due to the computational complexity of the problem. Previous work on discriminative parsing falls under one of three approaches. One approach does discriminative reranking of the 7-best list of a generative parser still usually depending highly on the generative parser score as a feature Collins 2000 Charniak and Johnson 2005 . A second group of papers does parsing by a sequence of independent discriminative decisions either greedily or with use of a .