Update app.py

app.py

@@ -20,39 +20,50 @@ def calculate_similarities(sentence1, sentence2):
     
     return float(wordllama_score), float(tfidf_score)
 
-# Examples combining original and new homophone-based examples
+# Carefully selected examples to compare both methods
 examples = [
-    # Original examples
-    ["I went to the car", "I went to the pawn shop"],
-    ["The cat is on the roof", "A dog is in the yard"],
-    ["She loves playing tennis", "She enjoys sports"],
-    ["This is a bright day", "It's a sunny morning"],
-    ["I bought a new phone", "I got a new mobile"],
-    ["The restaurant serves delicious food", "This place has great cuisine"],
-    ["Python is a programming language", "Java is used for coding"],
-    ["The movie was entertaining", "I enjoyed watching the film"],
-    ["Climate change affects our planet", "Global warming is a serious issue"],
-    ["Students study in the library", "People read books in the library"],
+    # High similarity in both methods
+    ["The cat is sleeping on the couch", "The cat is resting on the sofa"],
+    ["I love eating pizza", "I enjoy eating pizza"],
+    ["The weather is sunny today", "It is a sunny day today"],
     
-    # New examples with similar words but different meanings
-    ["The executive board met this morning", "I was so bored during the meeting"],
-    ["Don't waste your time on this", "The dress fits perfectly at the waist"],
-    ["The principal called a meeting", "It's a matter of principle"],
-    ["The weather is beautiful today", "I don't know whether to go or stay"],
-    ["I need a piece of the cake", "The world needs peace"],
-    ["The bass was swimming in the lake", "Turn up the bass in the speaker"],
-    ["The fair is in town this weekend", "That decision wasn't fair at all"],
-    ["I need to address this letter", "What's your new address?"],
-    ["The bank of the river is muddy", "I need to go to the bank for money"],
-    ["Can you bear this weight?", "I saw a bear in the woods"]
+    # Medium similarity in both methods
+    ["She is reading a book", "She is holding a novel"],
+    ["The car is red", "The automobile is crimson"],
+    ["The children are playing in the park", "Kids are having fun at the playground"],
+    
+    # Cases where WordLlama should perform better
+    ["The food was great", "The meal was excellent"],
+    ["The student is studying hard", "The pupil is working diligently"],
+    ["This movie is fantastic", "This film is amazing"],
+    
+    # Cases where TF-IDF should perform better
+    ["The red car is parked", "The red car is moving"],
+    ["The book is on the table", "The book is under the table"],
+    ["She went to the store", "She went to the mall"],
+    
+    # Semantic similarity cases
+    ["The laptop is expensive", "The computer costs a lot"],
+    ["The dog is barking", "The canine is making noise"],
+    ["The house is large", "The home is spacious"],
+    
+    # Word order importance cases
+    ["The cat chased the mouse", "The mouse chased the cat"],
+    ["John gave Mary a book", "Mary gave John a book"],
+    ["The teacher helped the student", "The student helped the teacher"],
+    
+    # Synonym cases
+    ["The car is fast", "The vehicle is quick"],
+    ["The building is tall", "The structure is high"],
+    ["The food is delicious", "The cuisine is tasty"]
 ]
 
 # Define Gradio interface with updated layout
 with gr.Blocks(theme=gr.themes.Soft()) as iface:
-    gr.Markdown("# Advanced Text Similarity Comparison")
+    gr.Markdown("# Text Similarity Comparison")
     gr.Markdown("""
     Compare sentences using both WordLlama and TF-IDF similarity metrics.
-    This tool includes examples of similar words with different meanings to demonstrate semantic understanding.
+    Examples are categorized to demonstrate strengths of each method.
     """)
     
     with gr.Row():
@@ -87,16 +98,15 @@ with gr.Blocks(theme=gr.themes.Soft()) as iface:
     
     gr.Markdown("""
     ### Understanding the Scores
-    - **WordLlama Similarity**: Measures semantic similarity considering context and meaning
-    - **TF-IDF Similarity**: Measures similarity based on word frequency and importance
-    """)
+    - **WordLlama Similarity**: Better at understanding semantic meaning and context
+    - **TF-IDF Similarity**: Better at exact word matching and frequency-based comparison
     
-    gr.Markdown("### Example Sentence Pairs")
-    gr.Markdown("""
-    The examples include:
-    - Regular sentence pairs
-    - Sentences with similar words but different meanings (homophones)
-    - Contextually related sentences
+    ### Example Categories
+    1. High Similarity: Both methods should show high scores
+    2. Medium Similarity: Both methods should show moderate scores
+    3. Semantic Similarity: WordLlama typically performs better
+    4. Word Order Cases: Shows how each method handles word order
+    5. Synonym Cases: Tests semantic understanding
     """)
     
     button.click(