File size: 1,168 Bytes
514343b
 
843aeb0
 
9983408
 
843aeb0
44264ed
 
88993fe
9983408
418bd7c
 
88993fe
44264ed
20efea7
418bd7c
20efea7
88993fe
20efea7
 
 
 
 
88993fe
3a19224
418bd7c
 
 
fee5ced
88993fe
 
c996dc1
fee5ced
 
 
b1d589a
20efea7
fee5ced
 
2832187
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
34
35
36
37
38
39
40
41
42

import streamlit as st
from transformers import pipeline
from textblob import TextBlob
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity

model = SentenceTransformer('paraphrase-xlm-r-multilingual-v1')

sentences = []
     
# Streamlit interface
      
st.title("Sentence Similarity")

# Streamlit form elements

with st.form("submission_form", clear_on_submit=False):

       sentence_1 = st.text_input("Sentence 1 input")
       
       sentence_2 = st.text_input("Sentence 2 input")
       
       submit_button = st.form_submit_button("Compare Sentences")

if submit_button:

       # Perform calculations
       
       # Append input sentences to 'sentences' list
       sentences.append(sentence_1)
       sentences.append(sentence_2)
       
       # Create embeddings for both sentences
       sentence_embeddings = model.encode(sentences)
      
              
       st.write('Similarity between {} and {} is {}%'.format(sentence_1,
              sentence_2,
              cosine_similarity(sentence_embeddings[0].reshape(1, -1),
              sentence_embeddings[1].reshape(1, -1))[0][0]) * 100)