Update app.py

app.py

@@ -5,33 +5,124 @@ import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
+from collections import defaultdict
 
-# Ensure necessary NLTK data is downloaded
+# Initialize the English text classification pipeline for AI detection
+pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
+
+# Function to predict the label and score for English text (AI Detection)
+def predict_en(text):
+    res = pipeline_en(text)[0]
+    return res['label'], res['score']
+
+# Ensure necessary NLTK data is downloaded for Humanifier
 nltk.download('wordnet')
 nltk.download('omw-1.4')
 
-# Ensure the SpaCy model is installed
+# Ensure the SpaCy model is installed for Humanifier
 try:
     nlp = spacy.load("en_core_web_sm")
 except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Initialize the English text classification pipeline for AI detection
-pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
-
-# Function to predict the label and score for English text (AI Detection)
-def predict_en(text):
-    res = pipeline_en(text)[0]
-    return res['label'], res['score']
-
 # Function to get synonyms using NLTK WordNet (Humanifier)
 def get_synonyms_nltk(word, pos):
     synsets = wordnet.synsets(word, pos=pos)
-    if synsets:
-        lemmas = synsets[0].lemmas()
-        return [lemma.name() for lemma in lemmas]
-    return []
+    synonyms = set()
+    for synset in synsets:
+        for lemma in synset.lemmas():
+            if lemma.name() != word:
+                synonyms.add(lemma.name())
+    return list(synonyms)
+
+# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
+def capitalize_sentences_and_nouns(text):
+    doc = nlp(text)
+    corrected_text = []
+
+    for sent in doc.sents:
+        sentence = []
+        for token in sent:
+            if token.i == sent.start:  # First word of the sentence
+                sentence.append(token.text.capitalize())
+            elif token.pos_ == "PROPN":  # Proper noun
+                sentence.append(token.text.capitalize())
+            else:
+                sentence.append(token.text)
+        corrected_text.append(' '.join(sentence))
+
+    return ' '.join(corrected_text)
+
+# Function to correct tense errors in a sentence (Tense Correction)
+def correct_tense_errors(text):
+    doc = nlp(text)
+    corrected_text = []
+
+    for token in doc:
+        if token.pos_ == "VERB":
+            # Check if verb is in its base form
+            if token.tag_ == "VB" and token.text.lower() not in ["be", "have", "do"]:
+                # Attempt to correct verb form based on sentence context
+                context = " ".join([t.text for t in doc if t.i != token.i])
+                corrected_text.append(token.lemma_)
+            else:
+                corrected_text.append(token.text)
+        else:
+            corrected_text.append(token.text)
+
+    return ' '.join(corrected_text)
+
+# Function to correct singular/plural errors (Singular/Plural Correction)
+def correct_singular_plural_errors(text):
+    doc = nlp(text)
+    corrected_text = []
+
+    # Create a context dictionary for singular/plural determination
+    context = defaultdict(int)
+    for token in doc:
+        if token.pos_ == "NOUN":
+            # Track context for noun usage
+            if token.tag_ == "NNS":
+                context['plural'] += 1
+            elif token.tag_ == "NN":
+                context['singular'] += 1
+
+    for token in doc:
+        if token.pos_ == "NOUN":
+            if token.tag_ == "NN":  # Singular noun
+                if context['plural'] > context['singular']:
+                    corrected_text.append(token.lemma_ + 's')
+                else:
+                    corrected_text.append(token.text)
+            elif token.tag_ == "NNS":  # Plural noun
+                if context['singular'] > context['plural']:
+                    corrected_text.append(token.lemma_)
+                else:
+                    corrected_text.append(token.text)
+            else:
+                corrected_text.append(token.text)
+        else:
+            corrected_text.append(token.text)
+
+    return ' '.join(corrected_text)
+
+# Function to check and correct article errors
+def correct_article_errors(text):
+    doc = nlp(text)
+    corrected_text = []
+    for token in doc:
+        if token.text in ['a', 'an']:
+            next_token = token.nbor(1)
+            if token.text == "a" and next_token.text[0].lower() in "aeiou":
+                corrected_text.append("an")
+            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
+                corrected_text.append("a")
+            else:
+                corrected_text.append(token.text)
+        else:
+            corrected_text.append(token.text)
+    return ' '.join(corrected_text)
 
 # Paraphrasing function using SpaCy and NLTK (Humanifier)
 def paraphrase_with_spacy_nltk(text):
@@ -41,37 +132,37 @@ def paraphrase_with_spacy_nltk(text):
     for token in doc:
         # Map SpaCy POS tags to WordNet POS tags
         pos = None
-        if token.pos_ in {"NOUN"}:
+        if token.pos_ == "NOUN":
             pos = wordnet.NOUN
-        elif token.pos_ in {"VERB"}:
+        elif token.pos_ == "VERB":
             pos = wordnet.VERB
-        elif token.pos_ in {"ADJ"}:
+        elif token.pos_ == "ADJ":
             pos = wordnet.ADJ
-        elif token.pos_ in {"ADV"}:
+        elif token.pos_ == "ADV":
             pos = wordnet.ADV
         
         synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else []
         
         # Replace with a synonym only if it makes sense
-        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower():
+        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"}:
             paraphrased_words.append(synonyms[0])
         else:
             paraphrased_words.append(token.text)
     
-    # Join the words back into a sentence
-    paraphrased_sentence = ' '.join(paraphrased_words)
-    
-    return paraphrased_sentence
+    return ' '.join(paraphrased_words)
 
 # Combined function: Paraphrase -> Grammar Correction -> Capitalization (Humanifier)
 def paraphrase_and_correct(text):
     # Step 1: Paraphrase the text
     paraphrased_text = paraphrase_with_spacy_nltk(text)
     
-    # Additional steps (grammar correction, capitalization) can go here...
-    # For now, we'll return the paraphrased text as an example.
+    # Step 2: Apply grammatical corrections on the paraphrased text
+    corrected_text = correct_article_errors(paraphrased_text)
+    corrected_text = capitalize_sentences_and_nouns(corrected_text)
+    corrected_text = correct_singular_plural_errors(corrected_text)
+    final_text = correct_tense_errors(corrected_text)
     
-    return paraphrased_text
+    return final_text
 
 # Gradio app setup with two tabs
 with gr.Blocks() as demo: