diff --git a/chapter_natural-language-processing-applications/finetuning-bert.md b/chapter_natural-language-processing-applications/finetuning-bert.md
index e13fa323fa..d21446af16 100644
--- a/chapter_natural-language-processing-applications/finetuning-bert.md
+++ b/chapter_natural-language-processing-applications/finetuning-bert.md
@@ -139,7 +139,7 @@ is just a segment of text (text span) from the passage that the question is abou
 To explain,
 consider a passage
 "Some experts report that a mask's efficacy is inconclusive. However, mask makers insist that their products, such as N95 respirator masks, can guard against the virus."
-and a question "Who say that N95 respirator masks can guard against the virus?".
+and a question "Who says that N95 respirator masks can guard against the virus?".
 The answer should be the text span "mask makers" in the passage.
 Thus, the goal in SQuAD v1.1 is to predict the start and end of the text span in the passage given a pair of question and passage.
 
diff --git a/chapter_natural-language-processing-applications/natural-language-inference-and-dataset.md b/chapter_natural-language-processing-applications/natural-language-inference-and-dataset.md
index b50283425f..066fe4be80 100644
--- a/chapter_natural-language-processing-applications/natural-language-inference-and-dataset.md
+++ b/chapter_natural-language-processing-applications/natural-language-inference-and-dataset.md
@@ -4,7 +4,7 @@
 In :numref:`sec_sentiment`, we discussed the problem of sentiment analysis.
 This task aims to classify a single text sequence into predefined categories,
 such as a set of sentiment polarities.
-However, when there is a need to decide whether one sentence can be inferred form another, 
+However, when there is a need to decide whether one sentence can be inferred from another, 
 or eliminate redundancy by identifying sentences that are semantically equivalent,
 knowing how to classify one text sequence is insufficient.
 Instead, we need to be able to reason over pairs of text sequences.