Update pages/Introduction.py
Browse files- pages/Introduction.py +17 -0
pages/Introduction.py
CHANGED
|
@@ -27,3 +27,20 @@ st.write("Example: _'I love NLP. It’s fascinating!'_ → [‘I love NLP.’,
|
|
| 27 |
st.write("**b. Stopword Removal**")
|
| 28 |
st.write("Removes common words like “the,” “and,” “is” that do not contribute much to analysis.")
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
st.write("**b. Stopword Removal**")
|
| 28 |
st.write("Removes common words like “the,” “and,” “is” that do not contribute much to analysis.")
|
| 29 |
|
| 30 |
+
st.write("**c. Stemming and Lemmatization**")
|
| 31 |
+
st.write("Stemming: Reduces words to their base or root form by chopping off suffixes (may not produce valid words).")
|
| 32 |
+
st.write("Example: _“running” _ → “run”")
|
| 33 |
+
|
| 34 |
+
st.write("Lemmatization: Converts words to their base form using vocabulary and grammar")
|
| 35 |
+
st.write("Example: _“good” _ → “better”")
|
| 36 |
+
|
| 37 |
+
st.write("**d. Part-of-Speech (POS) Tagging**")
|
| 38 |
+
st.write("Labels words with their grammatical roles (noun, verb, adjective, etc.)")
|
| 39 |
+
st.write("Example: _The cat sleeps”_ → [“The/DET”, “cat/NOUN”, “sleeps/VERB”]")
|
| 40 |
+
|
| 41 |
+
st.write("**e. Named Entity Recognition (NER)**")
|
| 42 |
+
st.write("Identifies and classifies entities in text (e.g., names, dates, locations)")
|
| 43 |
+
st.write("Example: _ “Barack Obama was born in Hawaii. _ ” → [Barack Obama: PERSON, Hawaii: LOCATION]")
|
| 44 |
+
|
| 45 |
+
st.write("**f. Text Normalization**")
|
| 46 |
+
st.write("Converts text to a standard format (lowercasing, removing punctuation, etc.).")
|