Open yangky11 opened 4 years ago
I tried to follow the instructions here for converting CTB to dependency trees. However, I have 1832 errors out of 17498 training trees when using Stanford Parser 3.3.0. The number of errors reduces to 124 when using Stanford Parser 3.9.2. I would appreciate it if sufficient details can be released to reproduce the CTB numbers in the paper. Thanks!
Same issue
Hi,
I have followed distance-parser to preprocess the CTB data, but what are the exact steps for generating dependency trees (They only do constituency parsing)? Thank you!