File size: 1,123 Bytes
ec1e4e7 94c0025 ec1e4e7 2db744e ec1e4e7 2db744e ec1e4e7 2db744e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 |
import streamlit as st
import numpy as np
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
# Set page title
st.set_page_config(page_title='Sentence Similarity Demo')
# Create a title for the app
st.title('Sentence Similarity Demo')
# Input sentences
sentence1 = st.text_input('Enter the first sentence:', 'Convert this into a sea shanty')
sentence2 = st.text_input('Enter the second sentence:', 'Improve this text by making it a shanty.')
@st.cache_resource
def load_model():
return SentenceTransformer('sentence-transformers/sentence-t5-base')
model = load_model()
# Calculate embeddings
embeddings = model.encode([sentence1, sentence2])
# Calculate Sharpened Cosine Similarity (SCS)
def sharpened_cosine_similarity(s, k, q=1e-6, p=2):
cosine_sim = np.dot(s, k) / (np.linalg.norm(s) * np.linalg.norm(k))
return np.sign(cosine_sim) * np.power(np.abs(cosine_sim) / (np.linalg.norm(s) + q), p)
similarity = sharpened_cosine_similarity(embeddings[0], embeddings[1])
# Display the result
st.write(f'Sharpened Cosine Similarity: {similarity:.4f}') |