Abstract | ||
---|---|---|
We present an improved training strategy for dependency parsers that use online reordering to handle non-projective trees. The new strategy improves both efficiency and accuracy by reducing the number of swap operations performed on non-projective trees by up to 80%. We present state-of-the-art results for five languages with the best ever reported results for Czech. |
Year | Venue | Keywords |
---|---|---|
2009 | IWPT | improved oracle,dependency parsers,new strategy,state-of-the-art result,improved training strategy,online reordering,non-projective tree,swap operation,dependency parsing,computational linguistics |
Field | DocType | Citations |
Czech,Programming language,Computer science,Computational linguistics,Oracle,Dependency grammar,Artificial intelligence,Natural language processing,Parsing,Swap (finance) | Conference | 23 |
PageRank | References | Authors |
1.20 | 7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joakim Nivre | 1 | 3652 | 229.07 |
Marco Kuhlmann | 2 | 309 | 23.06 |
Johan Hall | 3 | 520 | 33.55 |