Commit 45650c41 authored by Sinan Tan's avatar Sinan Tan Committed by xuehui
Browse files

Fix a bug when using official GLoVE embedding.

parent fb08ee59
...@@ -88,11 +88,13 @@ def load_embedding(path): ...@@ -88,11 +88,13 @@ def load_embedding(path):
''' '''
return embedding for a specif file by given file path. return embedding for a specif file by given file path.
''' '''
EMBEDDING_DIM = 300
embedding_dict = {} embedding_dict = {}
with open(path, 'r', encoding='utf-8') as file: with open(path, 'r', encoding='utf-8') as file:
pairs = [line.strip('\r\n').split() for line in file.readlines()] pairs = [line.strip('\r\n').split() for line in file.readlines()]
for pair in pairs: for pair in pairs:
embedding_dict[pair[0]] = [float(x) for x in pair[1:]] if len(pair) == EMBEDDING_DIM + 1:
embedding_dict[pair[0]] = [float(x) for x in pair[1:]]
logger.debug('embedding_dict size: %d', len(embedding_dict)) logger.debug('embedding_dict size: %d', len(embedding_dict))
return embedding_dict return embedding_dict
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment