|
|
|
|
|
|
by kylebgorman
4093 days ago
|
|
|
For comparability, most people use the Penn Treebank-III WSJ data. Sections 03-06 are test, the remaining sections are train/dev. Most methods are based on some sort of simple feature templates and machine learning, so they should generalize relatively well to a wide variety of languages, IMO. |
|
|