Update app.py

app.py

@@ -25,139 +25,65 @@ except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# 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 []
+# Function to get synonyms using NLTK WordNet and keep the same grammatical form
+def get_synonym(word, pos_tag):
+    synsets = wordnet.synsets(word)
+    if not synsets:
+        return word
+    
+    for synset in synsets:
+        if synset.pos() == pos_tag:  # Match the part of speech
+            synonym = synset.lemmas()[0].name()  # Get the first lemma
+            # Check if the original word and synonym are in the same form (singular/plural, tense, etc.)
+            if word.islower():
+                return synonym.lower()
+            else:
+                return synonym.capitalize()
+    return word
 
-# Updated function to replace words with synonyms while preserving verb forms and pluralization
-def replace_with_synonyms(text):
+# Function to rephrase text and replace words with their synonyms while maintaining form
+def rephrase_with_synonyms(text):
     doc = nlp(text)
-    replaced_words = {}
-    corrected_text = []
+    rephrased_text = []
 
     for token in doc:
-        word = token.text
-        pos = token.pos_
-
-        # Get the WordNet POS tag format
-        if pos == "VERB":
-            wordnet_pos = wordnet.VERB
-        elif pos == "NOUN":
-            wordnet_pos = wordnet.NOUN
-        elif pos == "ADJ":
-            wordnet_pos = wordnet.ADJ
-        elif pos == "ADV":
-            wordnet_pos = wordnet.ADV
-        else:
-            corrected_text.append(word)  # No change for other POS
-            continue
-
-        # Get synonyms for the word based on POS
-        if word in replaced_words:
-            synonym = replaced_words[word]
+        # Get the correct POS tag for WordNet
+        pos_tag = None
+        if token.pos_ == "NOUN":
+            pos_tag = wordnet.NOUN
+        elif token.pos_ == "VERB":
+            pos_tag = wordnet.VERB
+        elif token.pos_ == "ADJ":
+            pos_tag = wordnet.ADJ
+        elif token.pos_ == "ADV":
+            pos_tag = wordnet.ADV
+        
+        if pos_tag:
+            synonym = get_synonym(token.text, pos_tag)
+            # Ensure that the verb/noun/plural/singular is kept intact
+            if token.pos_ == "VERB":
+                synonym = token.lemma_ if token.morph.get("Tense") == "Past" else synonym
+            elif token.pos_ == "NOUN" and token.tag_ == "NNS":  # Plural nouns
+                synonym += 's' if not synonym.endswith('s') else ""
+            rephrased_text.append(synonym)
         else:
-            synonyms = get_synonyms_nltk(word, wordnet_pos)
-            if synonyms:
-                synonym = synonyms[0]  # Use the first synonym
-                # Ensure the synonym retains the same form (e.g., plural, verb form)
-                if pos == "VERB":
-                    synonym = token.lemma_ if synonym == token.lemma_ else token._.inflect(token.tag_)
-                if pos == "NOUN" and token.tag_ == "NNS":  # If plural noun, make sure synonym is plural
-                    synonym += 's'
-                replaced_words[word] = synonym
-            else:
-                synonym = word  # No synonym found, keep the word as is
-
-        corrected_text.append(synonym)
+            rephrased_text.append(token.text)
 
-    return ' '.join(corrected_text)
+    return ' '.join(rephrased_text)
 
-# 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 paraphrase and correct grammar with stronger synonym usage
+# Function to paraphrase and correct grammar
 def paraphrase_and_correct(text):
     paraphrased_text = capitalize_sentences_and_nouns(text)  # Capitalize first to ensure proper noun capitalization
     
-    # Replace words with their synonyms
-    paraphrased_text = replace_with_synonyms(paraphrased_text)
-
-    # Apply grammatical corrections (can include other corrections from the original functions)
+    # Apply grammatical corrections
     paraphrased_text = correct_article_errors(paraphrased_text)
     paraphrased_text = correct_singular_plural_errors(paraphrased_text)
     paraphrased_text = correct_tense_errors(paraphrased_text)
-
-    return paraphrased_text
-
-# 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)
-
-# Correct singular/plural errors
-def correct_singular_plural_errors(text):
-    doc = nlp(text)
-    corrected_text = []
     
-    for token in doc:
-        if token.pos_ == "NOUN":
-            if token.tag_ == "NN":  # Singular noun
-                if any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
-                    corrected_text.append(token.lemma_ + 's')
-                else:
-                    corrected_text.append(token.text)
-            elif token.tag_ == "NNS":  # Plural noun
-                if any(child.text.lower() in ['a', 'one'] for child in token.head.children):
-                    corrected_text.append(token.lemma_)
-                else:
-                    corrected_text.append(token.text)
-        else:
-            corrected_text.append(token.text)
+    # Rephrase with synonyms while maintaining grammatical forms
+    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
     
-    return ' '.join(corrected_text)
-
-# Correct tense errors in verbs
-def correct_tense_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
-            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
-            corrected_text.append(lemma)
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
+    return paraphrased_text
 
 # Gradio app setup with two tabs
 with gr.Blocks() as demo: