diff --git a/index.html b/index.html
index 240cb75..1b767d0 100644
--- a/index.html
+++ b/index.html
@@ -355,7 +355,7 @@ <h3 class="title is-4">Symbolic Labelling: Zero-shot labelling</h3>
 					<div class="content has-text-left step">
 						<p>
 							We use a pretrained <a href="https://pypi.org/project/open-clip-torch/">CLIP</a> model to predict the 
-							symbolic attribute that most-likely describes the entity. Notice that the entity labelled here (<code>C_shape = ⚫️</code>)
+							symbolic attribute that most-likely describes the entity. Notice that the attribute labelled here (<code>C_shape = ⚫️</code>)
 							ignores all other attributes of the entity.
 						</p> 
 					</div>
@@ -392,7 +392,7 @@ <h3 class="title is-4">Symbolic Embedding</h3>
 					<div class="content has-text-left step">
 						<p>
 							The symbolic labelling process is repeated for each entity in the scene. The resultant symbolic
-							vectors are concatenated to form a <em>symbolic embedding</em> of the scene.
+							vectors are stacked to form a <em>symbolic embedding</em> of the scene.
 						</p>
 					</div>
 					<br />