|
import torch |
|
import streamlit as st |
|
from transformers import RobertaTokenizer, RobertaForSequenceClassification |
|
import nltk |
|
from nltk.corpus import stopwords |
|
import re |
|
import string |
|
|
|
nltk.download('stopwords') |
|
nltk.download('punkt') |
|
stop_words = set(stopwords.words('english')) |
|
stop_words.discard('and') |
|
|
|
|
|
def tokenize_sentences(sentence): |
|
encoded_dict = tokenizer.encode_plus( |
|
sentence, |
|
add_special_tokens=True, |
|
max_length=128, |
|
padding='max_length', |
|
truncation=True, |
|
return_attention_mask=True, |
|
return_tensors='pt' |
|
) |
|
return torch.cat([encoded_dict['input_ids']], dim=0), torch.cat([encoded_dict['attention_mask']], dim=0) |
|
|
|
def remove_stop_words(sentence): |
|
words = nltk.word_tokenize(sentence) |
|
custom_words = ['recommend', 'having', 'Hello', 'best', 'restaurant', 'top', 'want', 'need', 'well', 'most', 'should', 'be', 'good', 'also'] |
|
stop_words.update(custom_words) |
|
words_without_stopwords = [word for word in words if word.lower() not in stop_words] |
|
sentence_without_stopwords = ' '.join(words_without_stopwords) |
|
return sentence_without_stopwords |
|
|
|
def preprocess_query(query): |
|
query = str(query).lower() |
|
query = query.strip() |
|
query = remove_stop_words(query) |
|
query=query.translate(str.maketrans("", "", string.punctuation)) |
|
return query |
|
|
|
def predict_aspects(sentence, threshold): |
|
input_ids, attention_mask = tokenize_sentences(sentence) |
|
with torch.no_grad(): |
|
outputs = aspects_model(input_ids, attention_mask=attention_mask) |
|
logits = outputs.logits |
|
predicted_aspects = torch.sigmoid(logits).squeeze().tolist() |
|
results = dict() |
|
for label, prediction in zip(LABEL_COLUMNS_ASPECTS, predicted_aspects): |
|
if prediction < threshold: |
|
continue |
|
precentage = round(float(prediction) * 100, 2) |
|
results[label] = precentage |
|
return results |
|
|
|
|
|
BERT_MODEL_NAME_FOR_ASPECTS_CLASSIFICATION = 'roberta-large' |
|
tokenizer = RobertaTokenizer.from_pretrained(BERT_MODEL_NAME_FOR_ASPECTS_CLASSIFICATION, do_lower_case=True) |
|
|
|
LABEL_COLUMNS_ASPECTS = ['FOOD-CUISINE', 'FOOD-DEALS', 'FOOD-DIET_OPTION', 'FOOD-EXPERIENCE', 'FOOD-FLAVOR', 'FOOD-GENERAL', 'FOOD-INGREDIENT', 'FOOD-KITCHEN', 'FOOD-MEAL', 'FOOD-MENU', 'FOOD-PORTION', 'FOOD-PRESENTATION', 'FOOD-PRICE', 'FOOD-QUALITY', 'FOOD-RECOMMENDATION', 'FOOD-TASTE', 'GENERAL-GENERAL', 'RESTAURANT-ATMOSPHERE', 'RESTAURANT-BUILDING', 'RESTAURANT-DECORATION', 'RESTAURANT-EXPERIENCE', 'RESTAURANT-FEATURES', 'RESTAURANT-GENERAL', 'RESTAURANT-HYGIENE', 'RESTAURANT-KITCHEN', 'RESTAURANT-LOCATION', 'RESTAURANT-OPTIONS', 'RESTAURANT-RECOMMENDATION', 'RESTAURANT-SEATING_PLAN', 'RESTAURANT-VIEW', 'SERVICE-BEHAVIOUR', 'SERVICE-EXPERIENCE', 'SERVICE-GENERAL', 'SERVICE-WAIT_TIME'] |
|
|
|
aspects_model = RobertaForSequenceClassification.from_pretrained(BERT_MODEL_NAME_FOR_ASPECTS_CLASSIFICATION, num_labels=len(LABEL_COLUMNS_ASPECTS)) |
|
aspects_model.load_state_dict(torch.load('./Aspects_Extraction_Model_updated.pth', map_location=torch.device('cpu'))) |
|
aspects_model.eval() |
|
|
|
|
|
st.title("Implicit and Explicit Aspect Extraction") |
|
|
|
sentence = st.text_input("Enter a sentence:") |
|
threshold = st.slider("Threshold", min_value=0.0, max_value=1.0, step=0.01, value=0.5) |
|
|
|
if sentence: |
|
processed_sentence = preprocess_query(sentence) |
|
results = predict_aspects(processed_sentence, threshold) |
|
if len(results) > 0: |
|
st.write("Predicted Aspects:") |
|
table_data = [["Aspect", "Probability"]] |
|
for aspect, percentage in results.items(): |
|
aspect_parts = aspect.split("-") |
|
table_data.append(aspect_parts + [f"{percentage}%"]) |
|
st.table(table_data) |
|
else: |
|
st.write("No aspects above the threshold.") |
|
|
|
|