|
|
import streamlit as st |
|
|
import zipfile |
|
|
import os |
|
|
import pandas as pd |
|
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline |
|
|
|
|
|
ZIP_FILE = "xnli-multilingual-nli-dataset.zip" |
|
|
EXTRACT_DIR = "extracted_data" |
|
|
|
|
|
@st.cache_data |
|
|
def extract_and_list_csv_files(): |
|
|
if not os.path.exists(EXTRACT_DIR): |
|
|
if not os.path.exists(ZIP_FILE): |
|
|
return [] |
|
|
with zipfile.ZipFile(ZIP_FILE, "r") as zip_ref: |
|
|
zip_ref.extractall(EXTRACT_DIR) |
|
|
return [f for f in os.listdir(EXTRACT_DIR) if f.endswith('.csv')] |
|
|
|
|
|
@st.cache_resource |
|
|
def load_nli_model(): |
|
|
tokenizer = AutoTokenizer.from_pretrained("MoritzLaurer/mDeBERTa-v3-base-mnli-xnli") |
|
|
model = AutoModelForSequenceClassification.from_pretrained("MoritzLaurer/mDeBERTa-v3-base-mnli-xnli") |
|
|
return pipeline("text-classification", model=model, tokenizer=tokenizer) |
|
|
|
|
|
st.set_page_config(page_title="Multilingual NLI Explorer", layout="centered") |
|
|
st.title("🌍 Multilingual NLI (Natural Language Inference) Explorer") |
|
|
st.markdown("Upload premise & hypothesis pairs or use the dataset to explore entailment, contradiction, or neutrality.") |
|
|
|
|
|
csv_files = extract_and_list_csv_files() |
|
|
|
|
|
if not csv_files: |
|
|
st.warning("⚠️ No CSV files found. Please make sure `xnli-multilingual-nli-dataset.zip` is uploaded.") |
|
|
else: |
|
|
selected_csv = st.selectbox("Choose a language CSV file:", csv_files) |
|
|
|
|
|
if selected_csv: |
|
|
file_path = os.path.join(EXTRACT_DIR, selected_csv) |
|
|
|
|
|
try: |
|
|
df = pd.read_csv(file_path).dropna() |
|
|
sample_df = df.sample(min(5, len(df))).reset_index(drop=True) |
|
|
|
|
|
st.subheader("📄 Sample from Dataset") |
|
|
st.dataframe(sample_df[['premise', 'hypothesis', 'label']]) |
|
|
|
|
|
st.subheader("🔍 Run Inference") |
|
|
index = st.number_input("Select Sample Index", min_value=0, max_value=len(sample_df)-1, value=0, step=1) |
|
|
premise = sample_df.loc[index, 'premise'] |
|
|
hypothesis = sample_df.loc[index, 'hypothesis'] |
|
|
|
|
|
st.markdown(f"**Premise:** {premise}") |
|
|
st.markdown(f"**Hypothesis:** {hypothesis}") |
|
|
|
|
|
if st.button("Run NLI Prediction"): |
|
|
nli_pipeline = load_nli_model() |
|
|
result = nli_pipeline(f"{premise} </s> {hypothesis}") |
|
|
st.success(f"**Prediction:** {result[0]['label']} (Score: {result[0]['score']:.2f})") |
|
|
except Exception as e: |
|
|
st.error(f"❌ Error reading CSV file: {e}") |
|
|
|
