Parsing (State of the art)

From ACL Wiki
Revision as of 11:30, 19 June 2007 by Slavpetrov (Talk | contribs)

Jump to: navigation, search

"Standard" measure:

PARSEVAL -- the evalb[1] program.

"Standard" datasets:

  • Training: WSJ sections 2-22
  • Testing: WSJ section 23
System Name Short Description Main Publications Software (if available) Results Comments (i.e. extra resources used, train/test times, ...)
Johnson & Charniak's Parser Lexicalized N-Best PCFG + Discriminative re-reanking Mark Johnson and Eugene Charniak, ACL 2005 [2] Available [3] 91.4 Works well also on Brown
Collins' Parser Lexicalized PCFG Collins' Thesis [4], Bikel's Thesis [5] Dan Bikel's Implementation [6]  ???
Berkeley Parser Automatically induced PCFG Petrov, Barrett, Thibaux and Klein, ACL 2006 [7], Petrov and Klein, NAACL 2007 [8] Available [9] 90.1

Works well also for Chinese and German