Streamline the usage notes around the examples

README.md

@@ -33,20 +33,20 @@ outputs = model.generate(**inputs, num_beams=5, max_new_tokens=256)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=False))
 ```
 
-Output:
+English output (`<S>` = subject, `<P>` = relation, `<O>` = object):
 
 ```text
 <S> Lina Dorado <P> birth year <O> 1975 <S> Lina Dorado <P> birth place <O> Bogotá
 ```
 
-For a Russian sentence, use the `Parse Russian` prefix:
+Russian example:
 
 ```text
 Input:  Parse Russian Валюта Индии - Индийская рупия.
 Output: <S> India <P> currency <O> Indian rupee
 ```
 
-The markers `<S>`, `<P>`, and `<O>` identify the subject, relation, and object of each triple. The reproduction code removes exact duplicate triples before evaluation.
+The scorer counts identical predicted triples only once per input.
 
 The [base model](https://huggingface.co/cointegrated/rut5-base-multitask) is distributed under MIT. The WebNLG data used for fine-tuning are distributed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/).