diff --git a/src/data_manager.py b/src/data_manager.py
index 74aeac1..f7908b7 100644
--- a/src/data_manager.py
+++ b/src/data_manager.py
@@ -386,7 +386,8 @@ def sample_sub_set_from_folder(path2texts, selected_cols,
         # By default, neither corpus cleaning nor language filtering are done
         clean_corpus = corpus_name in {
             'SemanticScholar', 'SemanticScholar_emb', 'patstat', 'patstat_emb',
-            'AEI_projects', 'CORDIS.parquet', 'S2CS.parquet'}
+            'AEI_projects', 'CORDIS.parquet', 'S2CS.parquet',
+            'cordis_evoc_vs_all', 'patstat_intersection_vs_all'}
         remove_non_en = corpus_name in {
             'SemanticScholar', 'SemanticScholar_emb', 'patstat', 'patstat_emb'}