Update app.py
Browse files
app.py
CHANGED
|
@@ -140,8 +140,14 @@ with st.expander("4️⃣ Vocabulary Layer (Vectorization)", expanded=True):
|
|
| 140 |
)
|
| 141 |
st.caption("Deletes overly common words (like 'paper' or 'study') that appear everywhere, preventing generic filler from dominating your themes.")
|
| 142 |
|
| 143 |
-
with st.expander("
|
| 144 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
if "MMR" in ui_extraction:
|
| 146 |
mmr_diversity = st.slider("MMR Diversity Penalty", 0.0, 1.0, 0.3)
|
| 147 |
else:
|
|
|
|
| 140 |
)
|
| 141 |
st.caption("Deletes overly common words (like 'paper' or 'study') that appear everywhere, preventing generic filler from dominating your themes.")
|
| 142 |
|
| 143 |
+
with st.expander("4️⃣ Extraction Layer (Representation)", expanded=True):
|
| 144 |
+
st.markdown("*BERTopic ALWAYS extracts baseline words using **c-TF-IDF** (Word Frequency). Do you want to apply an advanced mathematical filter on top of it?*")
|
| 145 |
+
|
| 146 |
+
ui_extraction = st.selectbox(
|
| 147 |
+
"Apply Advanced Filter:",
|
| 148 |
+
["None (Base c-TF-IDF only)", "KeyBERTInspired (Semantic alignment)", "MMR (Reduce redundancy)"]
|
| 149 |
+
)
|
| 150 |
+
|
| 151 |
if "MMR" in ui_extraction:
|
| 152 |
mmr_diversity = st.slider("MMR Diversity Penalty", 0.0, 1.0, 0.3)
|
| 153 |
else:
|