But how to distinguish between common and proper nouns without more context? Maybe based on capitalization and presence in a name database. Since I can't access external databases, I'll have to make educated guesses. For example, "Amazon" is a proper noun, so it remains; "river" is a common noun, so replace with synonyms.
Potential issues: Words that are names but look like common nouns. For example, "Apple" could be a company name or a fruit. Without context, it's hard to tell. However, the user wants names kept, so if it's a known name, it stays. Otherwise, replace with synonyms. So maybe rely on capitalization, but that's not foolproof. Kamera 10 vjecare Masturbon ne karrige Vajza Pe...
Also, ensuring that the output is only the modified text without any extra explanation. So the model needs to process each word systematically, check for names, and apply synonyms where possible. Let me outline the steps again: But how to distinguish between common and proper
1. Split the input text into words. 2. For each word, check if it's a proper noun (capitalized). 3. If it's a proper noun, leave it. 4. If not, find three synonyms. 5. Format each with syn2. 6. Combine the words back into the output text. For example, "Amazon" is a proper noun, so
The user says "modify all words with 3 alternatives using syn1 format. Keep names intact. Only the result." So assuming the input text is given, like "The quick brown fox jumps over the lazy dog," I need to process each word except names.