Update pages/Introduction.py
Browse files- pages/Introduction.py +6 -5
pages/Introduction.py
CHANGED
|
@@ -15,7 +15,7 @@ st.markdown("<p>NLP encompasses a wide array of techniques that aimed at enablin
|
|
| 15 |
|
| 16 |
st.write("**1. Text Processing and Preprocessing In NLP**")
|
| 17 |
st.write("Before performing any analysis or modeling, raw text data must be cleaned and prepared.")
|
| 18 |
-
st.
|
| 19 |
st.write("Splits text into smaller units like words or sentences.")
|
| 20 |
st.write("**Types:**")
|
| 21 |
|
|
@@ -25,21 +25,22 @@ st.write("Example: _'I love NLP'_ → [‘I’, ‘love’, ‘NLP’]")
|
|
| 25 |
st.write("**(ii) Sentence Tokenization:** Breaking text into sentences.")
|
| 26 |
st.write("Example: _'I love NLP. It’s fascinating!'_ → [‘I love NLP.’, ‘It’s fascinating!’]")
|
| 27 |
|
| 28 |
-
st.
|
| 29 |
st.write("Removes common words like “the,” “and,” “is” that do not contribute much to analysis.")
|
| 30 |
|
| 31 |
-
|
|
|
|
| 32 |
st.write("Stemming: Reduces words to their base or root form by chopping off suffixes (may not produce valid words).")
|
| 33 |
st.write("Example: _“running” _ → “run”")
|
| 34 |
|
| 35 |
st.write("Lemmatization: Converts words to their base form using vocabulary and grammar")
|
| 36 |
st.write("Example: _“good” _ → “better”")
|
| 37 |
|
| 38 |
-
st.
|
| 39 |
st.write("Labels words with their grammatical roles (noun, verb, adjective, etc.)")
|
| 40 |
st.write("Example: _The cat sleeps”_ → [“The/DET”, “cat/NOUN”, “sleeps/VERB”]")
|
| 41 |
|
| 42 |
-
st.
|
| 43 |
st.write("Identifies and classifies entities in text (e.g., names, dates, locations)")
|
| 44 |
st.write("Example: _ “Barack Obama was born in Hawaii. _ ” → [Barack Obama: PERSON, Hawaii: LOCATION]")
|
| 45 |
|
|
|
|
| 15 |
|
| 16 |
st.write("**1. Text Processing and Preprocessing In NLP**")
|
| 17 |
st.write("Before performing any analysis or modeling, raw text data must be cleaned and prepared.")
|
| 18 |
+
st.markdown('<p style="color:lightcoral;"><b>a. Tokenization</b></p>', unsafe_allow_html=True)
|
| 19 |
st.write("Splits text into smaller units like words or sentences.")
|
| 20 |
st.write("**Types:**")
|
| 21 |
|
|
|
|
| 25 |
st.write("**(ii) Sentence Tokenization:** Breaking text into sentences.")
|
| 26 |
st.write("Example: _'I love NLP. It’s fascinating!'_ → [‘I love NLP.’, ‘It’s fascinating!’]")
|
| 27 |
|
| 28 |
+
st.markdown('<p style="color:lightcoral;"><b>b. Stopword Removal</b></p>', unsafe_allow_html=True)
|
| 29 |
st.write("Removes common words like “the,” “and,” “is” that do not contribute much to analysis.")
|
| 30 |
|
| 31 |
+
|
| 32 |
+
st.markdown('<p style="color:lightcoral;"><b>c. Stemming and Lemmatization</b></p>', unsafe_allow_html=True)
|
| 33 |
st.write("Stemming: Reduces words to their base or root form by chopping off suffixes (may not produce valid words).")
|
| 34 |
st.write("Example: _“running” _ → “run”")
|
| 35 |
|
| 36 |
st.write("Lemmatization: Converts words to their base form using vocabulary and grammar")
|
| 37 |
st.write("Example: _“good” _ → “better”")
|
| 38 |
|
| 39 |
+
st.markdown('<p style="color:lightcoral;"><b>d. Part-of-Speech (POS) Tagging</b></p>', unsafe_allow_html=True)
|
| 40 |
st.write("Labels words with their grammatical roles (noun, verb, adjective, etc.)")
|
| 41 |
st.write("Example: _The cat sleeps”_ → [“The/DET”, “cat/NOUN”, “sleeps/VERB”]")
|
| 42 |
|
| 43 |
+
st.markdown('<p style="color:lightcoral;"><b>e. Named Entity Recognition (NER)</b></p>', unsafe_allow_html=True)
|
| 44 |
st.write("Identifies and classifies entities in text (e.g., names, dates, locations)")
|
| 45 |
st.write("Example: _ “Barack Obama was born in Hawaii. _ ” → [Barack Obama: PERSON, Hawaii: LOCATION]")
|
| 46 |
|