Update README.md

README.md

@@ -148,7 +148,7 @@ We set up a benchmark for evaluating robustness of automatic genre identificatio
 for the automatic enrichment of large text collections with genre information.
 You are welcome to submit your entry at the [benchmark's GitHub repository](https://github.com/TajaKuzman/AGILE-Automatic-Genre-Identification-Benchmark/tree/main).
 
-In an out-of-dataset scenario (evaluating a model on a [manually-annotated English EN-GINCO dataset](https://huggingface.co/datasets/TajaKuzman/X-GENRE-multilingual-text-genre-dataset) on which it was not trained),
+In an out-of-dataset scenario (evaluating a model on a manually-annotated English EN-GINCO dataset (available upon request)) on which it was not trained),
  the model outperforms all other technologies:
 
 |                             |   micro F1 |   macro F1 |   accuracy |
@@ -171,7 +171,8 @@ In an out-of-dataset scenario (evaluating a model on a [manually-annotated Engli
 
 An example of preparing data for genre identification and post-processing of the results can be found [here](https://github.com/TajaKuzman/Applying-GENRE-on-MaCoCu-bilingual) where we applied X-GENRE classifier to the English part of [MaCoCu](https://macocu.eu/) parallel corpora.
 
-For reliable results, genre classifier should be applied to documents of sufficient length (the rule of thumb is at least 75 words). It is advised that the predictions, predicted with confidence lower than 0.9, are not used. Furthermore, the label "Other" can be used as another indicator of low confidence of the predictions, as it often indicates that the text does not have enough features of any genre, and these predictions can be discarded as well.
+For reliable results, genre classifier should be applied to documents of sufficient length (the rule of thumb is at least 75 words).
+It is advised that the predictions, predicted with confidence higher than 0.9, are not used. Furthermore, the label "Other" can be used as another indicator of low confidence of the predictions, as it often indicates that the text does not have enough features of any genre, and these predictions can be discarded as well.
 
 After proposed post-processing (removal of low-confidence predictions, labels "Other" and in this specific case also label "Forum"), the performance on the MaCoCu data based on manual inspection reached macro and micro F1 of 0.92.
 
@@ -258,7 +259,7 @@ When applied on test splits of each of the datasets, the classifier performs wel
 | X-GENRE      | GINCO    |      0.749 |      0.758 |
 
 The classifier was compared with other classifiers on 2 additional genre datasets (to which the X-GENRE schema was mapped):
-- [EN-GINCO](https://huggingface.co/datasets/TajaKuzman/X-GENRE-multilingual-text-genre-dataset): a sample of the English enTenTen20 corpus
+- EN-GINCO (available upon request): a sample of the English enTenTen20 corpus
 - [FinCORE](https://github.com/TurkuNLP/FinCORE): Finnish CORE corpus
 
 | Trained on   | Tested on   |   Micro F1 |   Macro F1 |