The pretrained character and word embeddings are the same with the embeddings in the baseline of RichWordSegmentor
Character embeddings: gigaword_chn.all.a2b.uni.ite50.vec
Word(Lattice) embeddings: ctb.50d.vec
- Download the character embeddings and word embeddings and put them in the
data
folder. - excute from command -- 'python lattice.py config.cfg'