typos fix Chapter03.ipynb

rag-advanced/notebooks/Chapter03.ipynb

@@ -222,9 +222,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Pre-processing\n",
+    "## Preprocessing\n",
     "\n",
-    "Now that we have our raw data prepared and correctly tokenized, the next crucial step is to pre-process this data. Pre-processing is essential for removing extraneous information and formatting that could interfere with our language model's understanding of the content.\n",
+    "Now that we have our raw data prepared and correctly tokenized, the next crucial step is to pre-process this data. Preprocessing is essential for removing extraneous information and formatting that could interfere with our language model's understanding of the content.\n",
     "\n",
     "In this section, we'll focus on cleaning our data by removing markdown elements, special characters, and extra whitespace. This process will help streamline our text for more effective tokenization and ultimately improve the performance of our RAG system.\n",
     "\n",
@@ -304,7 +304,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Again, we can store the parsed data as a weave Dataset"
+    "Again, we can store the parsed data as a Weave dataset"
    ]
   },
   {
@@ -548,7 +548,7 @@
     "\n",
     "\n",
     "We are primarily interested in two aspects:\n",
-    "1. The impact of pre-processing on retrieval metrics\n",
+    "1. The impact of preprocessing on retrieval metrics\n",
     "2. The effect of different retrieval methods on response metrics\n",
     "\n",
     "To address these points, we will evaluate:\n",