Initial commit

app.py

@@ -0,0 +1,110 @@
+import warnings
+import torchvision
+import torch
+import pandas as pd
+from transformers.pipelines import pipeline
+from transformers import AutoTokenizer, AutoModel
+from sklearn.metrics.pairwise import cosine_similarity
+import streamlit as st
+
+# Suppress torchvision beta warnings
+torchvision.disable_beta_transforms_warning()
+warnings.filterwarnings("ignore", category=UserWarning, module="torchvision")
+
+# Initialize fill-mask pipeline and model/tokenizer for embedding
+pipe = pipeline("fill-mask", model="airesearch/wangchanberta-base-att-spm-uncased", framework="pt", use_fast=False)
+tokenizer = AutoTokenizer.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased", use_fast=False)
+model = AutoModel.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased")
+
+# Function to generate embeddings for full sentences
+def get_embedding(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+    return outputs.last_hidden_state[:, 0, :].cpu().numpy()
+
+# Streamlit app setup
+st.title("Thai Full Sentence Similarity App")
+# Explanation Section
+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.
+
+### 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
+
+### 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:", "ผู้ใช้งานท่าอากาศยานนานาชาติ <mask> มีกว่าสามล้านคน")
+
+# Ensure the input includes a `<mask>`
+if "<mask>" not in input_text:
+    input_text += " <mask>"
+    st.warning("`<mask>` token was missing in your input. It has been added automatically.")
+
+# 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)
+    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}")

requirements.txt

@@ -0,0 +1,6 @@
+torch
+transformers
+streamlit
+pandas
+scikit-learn
+torchvision