Initial commit

app.py

@@ -2,7 +2,7 @@ import warnings
 import torchvision
 import torch
 import pandas as pd
-from transformers import pipeline, AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModelForMaskedLM, pipeline
 from sklearn.metrics.pairwise import cosine_similarity
 import streamlit as st
 
@@ -10,41 +10,65 @@ import streamlit as st
 torchvision.disable_beta_transforms_warning()
 warnings.filterwarnings("ignore", category=UserWarning, module="torchvision")
 
-# Initialize fill-mask pipeline and model/tokenizer for embedding with slow tokenizer
-pipe = pipeline(
-    "fill-mask",
-    model="airesearch/wangchanberta-base-att-spm-uncased",
-    tokenizer=AutoTokenizer.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased", use_fast=False),
-    framework="pt"
-)
-model = AutoModel.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased")
-
-# Function to generate embeddings for full sentences
+# Load tokenizer and model with error handling for compatibility
+try:
+    tokenizer = AutoTokenizer.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased", use_fast=False)
+    model = AutoModelForMaskedLM.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased")
+    model_name = "airesearch/wangchanberta-base-att-spm-uncased"
+except Exception:
+    st.warning("Switching to xlm-roberta-base model due to compatibility issues.")
+    tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-base")
+    model = AutoModelForMaskedLM.from_pretrained("xlm-roberta-base")
+    model_name = "xlm-roberta-base"
+
+# Initialize the fill-mask pipeline
+pipe = pipeline("fill-mask", model=model, tokenizer=tokenizer, framework="pt")
+
+# Function to generate embeddings
 def get_embedding(text):
-    inputs = pipe.tokenizer(text, return_tensors="pt")
+    inputs = tokenizer(text, return_tensors="pt")
     with torch.no_grad():
         outputs = model(**inputs)
-    return outputs.last_hidden_state[:, 0, :].cpu().numpy()
+    return outputs.logits[:, 0, :].cpu().numpy()
 
 # Streamlit app setup
 st.title("Thai Full Sentence Similarity App")
 
-# Explanation of example usage
-st.markdown("""
-### Example Sentence with Mask:
-**Input:** `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน <mask> เพื่อสัมผัสธรรมชาติ"`
+st.write("""
+### How This App Works
+This app uses a mask-filling model to predict possible words or phrases that could fill in the `<mask>` token in a given sentence. It then calculates the similarity of each prediction with the original sentence to determine the most contextually appropriate completion.
+
+### Example Sentence
+In this example, we have the following sentence in Thai with a `<mask>` token:
+- **Input**: `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน <mask> เพื่อสัมผัสธรรมชาติ"`
+- **Translation**: "Many tourists choose to visit `<mask>` to experience nature."
+
+The `<mask>` token represents a location popular for its natural beauty.
 
-In this example, the model will replace `<mask>` with possible locations in Thailand, such as:
-- "เชียงใหม่" for "Chiang Mai"
-- "เขาใหญ่" for "Khao Yai"
-- "ภูเก็ต" for "Phuket"
+### Potential Predictions
+Here are some possible predictions the model might generate for `<mask>`:
+1. `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน เชียงใหม่ เพื่อสัมผัสธรรมชาติ"` - Chiang Mai
+2. `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน เขาใหญ่ เพื่อสัมผัสธรรมชาติ"` - Khao Yai
+3. `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน เกาะสมุย เพื่อสัมผัสธรรมชาติ"` - Koh Samui
+4. `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน ภูเก็ต เพื่อสัมผัสธรรมชาติ"` - Phuket
 
-The app will compute the similarity between the full sentences generated and the baseline sentence without `<mask>`.
+### Results Table
+For each prediction, the app calculates:
+- **Similarity Score**: Indicates how similar the predicted sentence is to the original input.
+- **Model Score**: Represents the model's confidence in the predicted word for `<mask>`.
+
+### Most Similar Prediction
+The app will display the most contextually similar prediction based on the similarity score. For example:
+- **Most Similar Prediction**: `"นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน เชียงใหม่ เพื่อสัมผัสธรรมชาติ"`
+- **Similarity Score**: 0.89
+- **Model Score**: 0.16
+
+Feel free to enter your own sentence with `<mask>` and explore the predictions!
 """)
 
 # User input box
 st.subheader("Input Text")
-input_text = st.text_input("Enter a sentence with `<mask>` to find similar predictions:", "นักท่องเที่ยวจำนวนมากเลือกที่จะไปเยือน <mask> เพื่อสัมผัสธรรมชาติ")
+input_text = st.text_input("Enter a sentence with `<mask>` to find similar predictions:", "ผู้ใช้งานท่าอากาศยานนานาชาติ <mask> มีกว่าสามล้านคน")
 
 # Ensure the input includes a `<mask>`
 if "<mask>" not in input_text:
@@ -53,42 +77,45 @@ if "<mask>" not in input_text:
 
 # Process the input when available
 if input_text:
-    # Display input text
     st.write(f"Input Text: {input_text}")
 
-    # Get baseline embedding for comparison (remove "<mask>" to get the full sentence)
+    # Generate baseline embedding (removing `<mask>` to get the full sentence)
     baseline_text = input_text.replace("<mask>", "")
     input_embedding = get_embedding(baseline_text)
 
     # Generate mask predictions and calculate similarity with the full sentences
     similarity_results = []
-    result = pipe(input_text)
-
-    for r in result:
-        # Full predicted sentence
-        prediction_text = r['sequence']
-
-        # Calculate embedding and similarity for the full sentence
-        prediction_embedding = get_embedding(prediction_text)
-        similarity = cosine_similarity(input_embedding, prediction_embedding)[0][0]
-
-        # Append results to the list
-        similarity_results.append({
-            "Prediction": prediction_text,
-            "Similarity Score": similarity,
-            "Model Score": r['score']
-        })
-
-    # Convert results to DataFrame for easy sorting and display
-    df_results = pd.DataFrame(similarity_results).sort_values(by="Similarity Score", ascending=False)
-
-    # Display all predictions sorted by similarity score
-    st.subheader("All Predictions Sorted by Similarity")
-    st.dataframe(df_results)
-
-    # Find and display the most similar prediction
-    most_similar = df_results.iloc[0]
-    st.subheader("Most Similar Prediction")
-    st.write(f"**Prediction**: {most_similar['Prediction']}")
-    st.write(f"**Similarity Score**: {most_similar['Similarity Score']:.4f}")
-    st.write(f"**Model Score**: {most_similar['Model Score']:.4f}")
+
+    try:
+        result = pipe(input_text)
+
+        for r in result:
+            # Adjust based on observed output structure
+            prediction_text = r.get('sequence', '')
+
+            # Only proceed if we have a valid prediction text
+            if prediction_text:
+                prediction_embedding = get_embedding(prediction_text)
+                similarity = cosine_similarity(input_embedding, prediction_embedding)[0][0]
+                similarity_results.append({
+                    "Prediction": prediction_text,
+                    "Similarity Score": similarity,
+                    "Model Score": r['score']
+                })
+
+        # Convert results to DataFrame for easy sorting and display
+        df_results = pd.DataFrame(similarity_results).sort_values(by="Similarity Score", ascending=False)
+
+        # Display all predictions sorted by similarity score
+        st.subheader("All Predictions Sorted by Similarity")
+        st.dataframe(df_results)
+
+        # Display the most similar prediction
+        most_similar = df_results.iloc[0]
+        st.subheader("Most Similar Prediction")
+        st.write(f"**Prediction**: {most_similar['Prediction']}")
+        st.write(f"**Similarity Score**: {most_similar['Similarity Score']:.4f}")
+        st.write(f"**Model Score**: {most_similar['Model Score']:.4f}")
+
+    except KeyError:
+        st.error("Unexpected model output structure; unable to retrieve predictions.")

requirements.txt

@@ -4,3 +4,4 @@ streamlit
 pandas
 scikit-learn
 torchvision
+sentencepiece