p71924506
/
deepke
1
0
Fork 0
Code Issues Pull Requests 1 Projects Releases Wiki Activity

fix bug

This commit is contained in:
tlk-dsg 2021-11-08 20:41:18 +08:00
parent 36ca19f69f
commit dc84f31e40
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/deepke/attribution_extraction/standard/tools/preprocess.py
View File

@ -53,10 +53,10 @@ def _convert_tokens_into_index(data: List[Dict], vocab):
d['token2idx'] = [vocab.word2idx.get(i, unk_idx) for i in d['tokens']]
d['seq_len'] = len(d['token2idx'])
def _serialize_sentence(data: List[Dict], serial, cfg):
def _serialize_sentence(data: List[Dict], serial):
for d in data:
sent = d['sentence'].strip()
snet = sent.replace(d['entity'] , ' entity ' , 1).replace(d['attribute_value'] , ' attribute_value ' , 1)
sent = sent.replace(d['entity'] , ' entity ' , 1).replace(d['attribute_value'] , ' attribute_value ' , 1)
d['tokens'] = serial(sent, never_split=['entity','attribute_value'])
entity_index, attribute_value_index = d['entity_offset'] , d['attribute_value_offset']
d['entity_index'],d['attribute_value_index'] = int(entity_index) , int(attribute_value_index)