Update README.md

README.md

@@ -54,5 +54,5 @@ You can use the model like this:
 >>> decoded = tokenizer.batch_decode(outputs, skip_special_tokens=False)[0]
 >>> print(decoded)
 
-<|question|>How is the text best described? : " Rate Book ", " Search Screening Event ", " Add To Playlist ", " Search Creative Work ", " Get Weather ", " Play Music ", " Book Restaurant "<|endoftext|><|text|>I'd like to have this track onto my Classical Relaxations playlist.<|endoftext|><|answer|>Play Media<|endoftext|>
+<|question|>Which of these categories best describes the following document? : " Play Music ", " Add To Playlist ", " Rate Book ", " Book Restaurant ", " Search Creative Work ", " Search Screening Event ", " Get Weather "<|endoftext|><|text|>intent[ASPECT_SEP]I'd like to have this track onto my Classical Relaxations playlist.<|endoftext|><|answer|>Play Media<|endoftext|>
 ```