if i wanna use my own corpus to train the model?

[marcusau]

which portion i have to amend?

[qiufengyuyi]

which portion i have to amend?

first，your own data should be like this: one line is a text split by blank,the second line is tag for each character.

海 钓 比 赛 地 点 在 厦 门 与 金 门 之 间 的 海 域 。
O O O O O O O B-LOC I-LOC O B-LOC I-LOC O O O O O O
second ,you should put the orig data file in data/
third,you shoud add your own slot_pattern_list file in data/slot_pattern/
lastly,you could use BaseDataPreparing to preprocessing data ,remember to set gen_new_data=True