These results compare the baseline model, which combines a standard word vector with a token-level character vector obtained by passing the characters of a word through a BiLSTM to the meta model. The meta model separates word and character features as separate views and then combines them.

cs_fictree

en_ewt

eu_bdt

fi_ftb

ga_idt

grc_proiel

he_htb

ja_gsd

zh_gsd