2004 MaxMarginParsing

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Max-Margin Classification, Natural Language Parsing Task.

Notes

Quotes

Abstract

  • We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic programs for parsing. In particular, it allows one to efficiently learn a model which discriminates among the entire space of parse trees, as opposed to reranking the top few candidates. Our models can condition on arbitrary features of input sentences, thus incorporating an important kind of lexical information without the added algorithmic coplexity of modeling headedness. We provide an efficient algorithm for learning such models and show experimental evidence of the model’s improved performance over a natural baseline model and a lexicalized probabilistic context-free grammar.

,

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2004 MaxMarginParsingMichael Collins
Daphne Koller
Dan Klein
Christopher D. Manning
Max-Margin Parsinghttp://www.aclweb.org/anthology/W/W04/W04-3201.pdf