diff --git a/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md b/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md
index 93a6cd1f7..91449867e 100644
--- a/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md
+++ b/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md
@@ -81,7 +81,7 @@ class TokenEmbedding:
         data_dir = d2l.download_extract(embedding_name)
         # GloVe website: https://nlp.stanford.edu/projects/glove/
         # fastText website: https://fasttext.cc/
-        with open(os.path.join(data_dir, 'vec.txt'), 'r') as f:
+        with open(os.path.join(data_dir, 'vec.txt'), 'r', encoding='utf-8') as f:
             for line in f:
                 elems = line.rstrip().split(' ')
                 token, elems = elems[0], [float(elem) for elem in elems[1:]]
diff --git a/d2l/mxnet.py b/d2l/mxnet.py
index 25fc6eaf3..80e6af6d8 100644
--- a/d2l/mxnet.py
+++ b/d2l/mxnet.py
@@ -2071,7 +2071,7 @@ def _load_embedding(self, embedding_name):
         data_dir = d2l.download_extract(embedding_name)
         # GloVe网站：https://nlp.stanford.edu/projects/glove/
         # fastText网站：https://fasttext.cc/
-        with open(os.path.join(data_dir, 'vec.txt'), 'r') as f:
+        with open(os.path.join(data_dir, 'vec.txt'), 'r', encoding='utf-8') as f:
             for line in f:
                 elems = line.rstrip().split(' ')
                 token, elems = elems[0], [float(elem) for elem in elems[1:]]
diff --git a/d2l/paddle.py b/d2l/paddle.py
index 6c5813aeb..fc03a9a8a 100644
--- a/d2l/paddle.py
+++ b/d2l/paddle.py
@@ -2201,7 +2201,7 @@ def _load_embedding(self, embedding_name):
         data_dir = d2l.download_extract(embedding_name)
         # GloVe网站：https://nlp.stanford.edu/projects/glove/
         # fastText网站：https://fasttext.cc/
-        with open(os.path.join(data_dir, 'vec.txt'), 'r') as f:
+        with open(os.path.join(data_dir, 'vec.txt'), 'r' , encoding='utf-8') as f:
             for line in f:
                 elems = line.rstrip().split(' ')
                 token, elems = elems[0], [float(elem) for elem in elems[1:]]