diff --git a/subtitles/en/41_text-embeddings-&-semantic-search.srt b/subtitles/en/41_text-embeddings-&-semantic-search.srt
index 51c9d9b29..5fc6dc369 100644
--- a/subtitles/en/41_text-embeddings-&-semantic-search.srt
+++ b/subtitles/en/41_text-embeddings-&-semantic-search.srt
@@ -194,12 +194,12 @@ average the token embeddings
 
 44
 00:01:49,650 --> 00:01:52,500
-which is called mean pooling
+which is called mean_pooling
 and this is what we do here.
 
 45
 00:01:53,370 --> 00:01:55,800
-With mean pooling the only
+With mean_pooling the only
 thing we need to make sure
 
 46
@@ -210,7 +210,7 @@ padding tokens in the average,
 47
 00:01:58,410 --> 00:02:01,860
 which is why you can see the
-attention mask being used here.
+attention_mask being used here.
 
 48
 00:02:01,860 --> 00:02:05,100
@@ -313,7 +313,7 @@ we take a small sample
 
 70
 00:02:56,070 --> 00:02:57,780
-from the SQUAD dataset and apply
+from the squad dataset and apply
 
 71
 00:02:57,780 --> 00:03:00,180