updated part 1

changed "more recent ones on LLMs (transformers)" to "more recent ones on LLMs (BERT)"

Author: mingyu-yuan

lessons/01_preprocessing.ipynb

@@ -28,7 +28,7 @@
     "1. [Preprocessing](#section1)\n",
     "2. [Tokenization](#section2)\n",
     "\n",
-    "In this three-part workshop series, we'll learn the building blocks for performing text analysis in Python. These techniques lie in the domain of Natural Language Processing (NLP). NLP is a field that deals with identifying and extracting patterns of language, primarily in written texts. Throughout the workshop series, we'll interact with various packages for performing text analysis: starting from simple string methods to specific NLP packages, such as `nltk`, `spaCy`, and more recent ones on Large Language Models (`transformers`).\n",
+    "In this three-part workshop series, we'll learn the building blocks for performing text analysis in Python. These techniques lie in the domain of Natural Language Processing (NLP). NLP is a field that deals with identifying and extracting patterns of language, primarily in written texts. Throughout the workshop series, we'll interact with various packages for performing text analysis: starting from simple string methods to specific NLP packages, such as `nltk`, `spaCy`, and more recent ones on Large Language Models (`BERT`).\n",
     "\n",
     "Now, let's have these packages properly installed before diving into the materials."
    ]