# Group datasets under broad semantic categories semantic_categories = { "Sentiment and Emotion Analysis": [ "iberbench/tass-tass-sentiment_analysis-2020-spanish-uruguay", "iberbench/tass-tass-sentiment_analysis-2020-spanish-mexico", "iberbench/tass-tass-sentiment_analysis-2020-spanish-spain", "iberbench/tass-tass-sentiment_analysis-2020-spanish-costa_rica", "iberbench/tass-tass-sentiment_analysis-2020-spanish-peru", "iberbench/tass-tass-emotion_analysis-2020-spanish", "iberbench/iberlef-restmex-sentiment_analysis-2022-spanish-mexico", "iberbench/iberlef-restmex-sentiment_analysis-2021-spanish-mexico", "iberbench/general-bec-sentiment_analysis-2024-basque", "iberbench/iberlef-emoevales-emotion_analysis-2021-spanish" ], "Toxicity and Harmful Language Detection": [ "iberbench/iberlef-detoxis-aggressiveness_detection-2021-spanish", "iberbench/iberlef-detoxis-toxicity_detection-2021-spanish", "iberbench/iberlef-detoxis-improper_language_detection-2021-spanish", "iberbench/iberlef-detoxis-insult_detection-2021-spanish", "iberbench/iberlef-detoxis-mockery_detection-2021-spanish", "iberbench/iberlef-emoevales-offensiveness_detection-2021-spanish", "iberbench/iberlef-meoffendes-offensiveness_detection-2021-spanish", "iberbench/iberlef-mex_a3t-aggressiveness_detection-2019-spanish-mexico", "iberbench/general-hate_check-hate_speech_detection-2024-portuguese" ], "Prejudice and Discrimination Detection": [ "iberbench/iberlef-detests_dis-stereotype_detection-2024-spanish", "iberbench/iberlef-exist-sexism_detection-2021-spanish", "iberbench/iberlef-exist-sexism_categorization-2021-spanish", "iberbench/iberlef-huhu-racial_prejudice_detection-2023-spanish", "iberbench/iberlef-huhu-women_prejudice_detection-2023-spanish", "iberbench/iberlef-huhu-lgtbiq_prejudice_detection-2023-spanish", "iberbench/iberlef-huhu-fatphobia_detection-2023-spanish" ], "Machine Generated Text Detection and Attribution": [ "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-galician", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-english", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-spanish", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-catalan", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-basque", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-english", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-portuguese", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-portuguese", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-basque", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-catalan", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-galician", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-spanish" ], "Irony and Sarcasm Detection": [ "iberbench/iberlef-detoxis-sarcasm_detection-2021-spanish", "iberbench/iberlef-irosva-irony_detection-2019-spanish-cuba", "iberbench/iberlef-irosva-irony_detection-2019-spanish-mexico", "iberbench/iberlef-irosva-irony_detection-2019-spanish-spain" ], "Mental Health Detection": [ "iberbench/iberlef-mentalriskes-eating_disorder_detection-2023-spanish", "iberbench/iberlef-mentalriskes-depression_detection-2023-spanish", "iberbench/iberlef-mentalriskes-depression_categorization-2023-spanish" ], "Stance Detection": [ "iberbench/iberlef-vaxxstance-stance_detection-2021-basque", "iberbench/iberlef-vaxxstance-stance_detection-2021-spanish", "iberbench/ibereval-multistancecat-stance_detection-2018-spanish", "iberbench/ibereval-multistancecat-stance_detection-2018-catalan" ], "Paraphrase Detection": [ "iberbench/iberlef-parmex-paraphrase_detection-2022-spanish-mexico", "iberbench/general-paws_x-paraphrase_detection-2019-spanish", "iberbench/general-paws_gl-paraphrase_detection-2019-galician", "iberbench/general-paws_pt-paraphrase_detection-2019-portuguese", "iberbench/general-paws_ca-paraphrase_detection-2019-catalan", "iberbench/general-parafraseja-paraphrase_detection-2022-catalan" ], "Author Profiling": [ "iberbench/pan-author_profiling-gender_detection-2017-spanish", "iberbench/pan-author_profiling-age_detection-2015-spanish", "iberbench/iberlef-meoffendes-gender_detection-2021-spanish", "iberbench/iberlef-restmex-gender_detection-2021-spanish-mexico" ], "Fake News Detection": [ "iberbench/iberlef-fakedes-fake_news_detection-2021-spanish" ], "Humor Detection": [ "iberbench/iberlef-haha-humor_detection-2021-spanish", "iberbench/iberlef-haha-humor_detection-2019-spanish", "iberbench/iberlef-huhu-humor_detection-2023-spanish" ], "Question Answering": [ "iberbench/general-eus_exams-question_answering-2024-basque", "iberbench/general-eus_exams-question_answering-2024-spanish", "iberbench/general-eus_trivia-question_answering-2024-basque", "iberbench/general-xstorycloze-question_answering-2024-galician", "iberbench/general-xstorycloze-question_answering-2024-portuguese", "iberbench/general-xstorycloze-question_answering-2024-catalan", "iberbench/general-openbook_qa-question_answering-2022-spanish", "iberbench/general-openbook_qa-question_answering-2022-catalan", "iberbench/general-arc-question_answering-2024-basque", "iberbench/general-arc-question_answering-2024-catalan" ], "Commonsense Reasoning": [ "iberbench/general-xcopa-commonsense_reasoning-2024-basque", "iberbench/general-copa_es-commonsense_reasoning-2024-spanish", "iberbench/general-piqa-commonsense_reasoning-2024-basque", "iberbench/general-copa-commonsense_reasoning-2024-catalan" ], "Reading Comprehension": [ "iberbench/general-eus_reading-reading_comprehension-2024-basque", "iberbench/general-belebele-reading_comprehension-2024-basque", "iberbench/general-belebele-reading_comprehension-2024-spanish", "iberbench/general-belebele-reading_comprehension-2024-portuguese", "iberbench/general-belebele-reading_comprehension-2024-catalan" ], "Topic Classification": [ "iberbench/general-eus_trivia-topic_classification-2024-basque", "iberbench/general-bhtc-topic_classification-2024-basque", "iberbench/general-clindiagnoses-topic_classification-2024-spanish" ], "Linguistic Acceptability": [ "iberbench/general-escola-linguistic_acceptability-2024-spanish", "iberbench/general-galcola-linguistic_acceptability-2024-galician", "iberbench/general-catcola-linguistic_acceptability-2024-catalan" ], "Textual Entailment": [ "iberbench/general-qnli-textual_entailment-2024-basque", "iberbench/general-xnli-textual_entailment-2024-spanish", "iberbench/general-xnli-textual_entailment-2024-galician", "iberbench/general-xnli-textual_entailment-2024-catalan", "iberbench/general-teca-textual_entailment-2021-catalan" ], "Intent Classification": [ "iberbench/general-fmtodeu-intent_classification-2024-basque" ], "Proficiency Evaluation": [ "iberbench/general-eus_proficiency-proficiency_evaluation-2024-basque", "iberbench/general-teleia-proficiency_evaluation-2024-spanish" ], "Text Summarization": [ "iberbench/general-xlsum-text_summarization-2021-spanish", "iberbench/general-xlsum-text_summarization-2021-portuguese", "iberbench/general-cabreu-text_summarization-2024-catalan" ], "Lexical Analysis": [ "iberbench/iberlef-adobo-lexical_borrowing_chunking-2021-spanish" ], "Language Identification": [ "iberbench/tweetlid-tweetlid-language_identification-2014-spanish" ] } # Group datasets in "fundamental" or "professional". # Fundamental tasks are those that evaluates knowledge and writting capabilities of LLMs. # Tasks like question answering on exams, reading comprehension, entailment, proficiency evaluation, linguistic acceptability, etc. are under this category. # Professional tasks are those that have economic interest for the industry. # Tasks like author profiling, sentiment analysis, machine-generated text detection, fake news detection, stance, discrimination, etc. are under this category. professional_mapping = { "Fundamental NLP": [ "iberbench/iberlef-adobo-lexical_borrowing_chunking-2021-spanish", "iberbench/general-eus_exams-question_answering-2024-basque", "iberbench/general-eus_exams-question_answering-2024-spanish", "iberbench/general-eus_trivia-topic_classification-2024-basque", "iberbench/general-eus_trivia-question_answering-2024-basque", "iberbench/general-eus_proficiency-proficiency_evaluation-2024-basque", "iberbench/general-xcopa-commonsense_reasoning-2024-basque", "iberbench/general-eus_reading-reading_comprehension-2024-basque", "iberbench/general-arc-question_answering-2024-basque", "iberbench/general-piqa-commonsense_reasoning-2024-basque", "iberbench/general-belebele-reading_comprehension-2024-basque", "iberbench/general-qnli-textual_entailment-2024-basque", "iberbench/general-copa_es-commonsense_reasoning-2024-spanish", "iberbench/general-openbook_qa-question_answering-2022-spanish", "iberbench/general-teleia-proficiency_evaluation-2024-spanish", "iberbench/general-belebele-reading_comprehension-2024-spanish", "iberbench/general-escola-linguistic_acceptability-2024-spanish", "iberbench/general-xnli-textual_entailment-2024-spanish", "iberbench/general-xnli-textual_entailment-2024-galician", "iberbench/general-galcola-linguistic_acceptability-2024-galician", "iberbench/general-xstorycloze-question_answering-2024-galician", "iberbench/general-belebele-reading_comprehension-2024-portuguese", "iberbench/general-xstorycloze-question_answering-2024-portuguese", "iberbench/general-xstorycloze-question_answering-2024-catalan", "iberbench/general-xnli-textual_entailment-2024-catalan", "iberbench/general-arc-question_answering-2024-catalan", "iberbench/general-belebele-reading_comprehension-2024-catalan", "iberbench/general-openbook_qa-question_answering-2022-catalan", "iberbench/general-copa-commonsense_reasoning-2024-catalan", "iberbench/general-catcola-linguistic_acceptability-2024-catalan", "iberbench/general-teca-textual_entailment-2021-catalan", ], "Industry NLP": [ "iberbench/iberlef-restmex-sentiment_analysis-2022-spanish-mexico", "iberbench/iberlef-restmex-sentiment_analysis-2021-spanish-mexico", "iberbench/general-parafraseja-paraphrase_detection-2022-catalan", "iberbench/general-paws_ca-paraphrase_detection-2019-catalan", "iberbench/general-cabreu-text_summarization-2024-catalan", "iberbench/general-xlsum-text_summarization-2021-portuguese", "iberbench/general-paws_pt-paraphrase_detection-2019-portuguese", "iberbench/general-paws_gl-paraphrase_detection-2019-galician", "iberbench/general-paws_x-paraphrase_detection-2019-spanish", "iberbench/general-clindiagnoses-topic_classification-2024-spanish", "iberbench/general-fmtodeu-intent_classification-2024-basque", "iberbench/general-bhtc-topic_classification-2024-basque", "iberbench/general-xlsum-text_summarization-2021-spanish", "iberbench/general-bec-sentiment_analysis-2024-basque", "iberbench/tass-tass-sentiment_analysis-2020-spanish-uruguay", "iberbench/tass-tass-sentiment_analysis-2020-spanish-mexico", "iberbench/tass-tass-sentiment_analysis-2020-spanish-spain", "iberbench/tass-tass-sentiment_analysis-2020-spanish-costa_rica", "iberbench/tass-tass-sentiment_analysis-2020-spanish-peru", "iberbench/tass-tass-emotion_analysis-2020-spanish", "iberbench/iberlef-emoevales-emotion_analysis-2021-spanish", "iberbench/iberlef-haha-humor_detection-2021-spanish", "iberbench/iberlef-haha-humor_detection-2019-spanish", "iberbench/iberlef-irosva-irony_detection-2019-spanish-cuba", "iberbench/iberlef-irosva-irony_detection-2019-spanish-mexico", "iberbench/iberlef-irosva-irony_detection-2019-spanish-spain", "iberbench/tweetlid-tweetlid-language_identification-2014-spanish", "iberbench/iberlef-parmex-paraphrase_detection-2022-spanish-mexico", "iberbench/iberlef-detests_dis-stereotype_detection-2024-spanish", "iberbench/iberlef-detoxis-aggressiveness_detection-2021-spanish", "iberbench/iberlef-detoxis-toxicity_detection-2021-spanish", "iberbench/iberlef-detoxis-improper_language_detection-2021-spanish", "iberbench/iberlef-detoxis-sarcasm_detection-2021-spanish", "iberbench/iberlef-detoxis-insult_detection-2021-spanish", "iberbench/iberlef-detoxis-mockery_detection-2021-spanish", "iberbench/iberlef-exist-sexism_detection-2021-spanish", "iberbench/iberlef-emoevales-offensiveness_detection-2021-spanish", "iberbench/iberlef-exist-sexism_categorization-2021-spanish", "iberbench/iberlef-fakedes-fake_news_detection-2021-spanish", "iberbench/iberlef-huhu-racial_prejudice_detection-2023-spanish", "iberbench/iberlef-huhu-women_prejudice_detection-2023-spanish", "iberbench/iberlef-huhu-lgtbiq_prejudice_detection-2023-spanish", "iberbench/iberlef-huhu-fatphobia_detection-2023-spanish", "iberbench/iberlef-huhu-humor_detection-2023-spanish", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-galician", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-english", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-spanish", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-catalan", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-basque", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-english", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-portuguese", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-portuguese", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-basque", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-catalan", "iberbench/iberlef-iberautextification-machine_generated_text_attribution-2024-galician", "iberbench/iberlef-iberautextification-machine_generated_text_detection-2024-spanish", "iberbench/iberlef-mentalriskes-eating_disorder_detection-2023-spanish", "iberbench/iberlef-vaxxstance-stance_detection-2021-basque", "iberbench/iberlef-vaxxstance-stance_detection-2021-spanish", "iberbench/ibereval-multistancecat-stance_detection-2018-spanish", "iberbench/iberlef-mex_a3t-aggressiveness_detection-2019-spanish-mexico", "iberbench/iberlef-meoffendes-offensiveness_detection-2021-spanish", "iberbench/iberlef-meoffendes-gender_detection-2021-spanish", "iberbench/iberlef-mentalriskes-depression_detection-2023-spanish", "iberbench/ibereval-multistancecat-stance_detection-2018-catalan", "iberbench/iberlef-mentalriskes-depression_categorization-2023-spanish", "iberbench/iberlef-restmex-gender_detection-2021-spanish-mexico", "iberbench/pan-author_profiling-gender_detection-2017-spanish", "iberbench/pan-author_profiling-age_detection-2015-spanish", "iberbench/general-hate_check-hate_speech_detection-2024-portuguese" ] }