huggingface · lhoestq · Apr 13, 2022 · Mar 30, 2022 · Mar 30, 2022 · Mar 30, 2022
diff --git a/datasets/acronym_identification/README.md b/datasets/acronym_identification/README.md
@@ -14,9 +14,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- structure-prediction
+- token-classification
 task_ids:
-- structure-prediction-other-acronym-identification
+- token-classification-other-acronym-identification
 paperswithcode_id: acronym-identification
 pretty_name: Acronym Identification Dataset
 ---

diff --git a/datasets/ade_corpus_v2/README.md b/datasets/ade_corpus_v2/README.md
@@ -22,9 +22,9 @@ task_categories:
   Ade_corpus_v2_classification:
   - text-classification
   Ade_corpus_v2_drug_ade_relation:
-  - structure-prediction
+  - token-classification
   Ade_corpus_v2_drug_dosage_relation:
-  - structure-prediction
+  - token-classification
 task_ids:
   Ade_corpus_v2_classification:
   - fact-checking

diff --git a/datasets/afrikaans_ner_corpus/README.md b/datasets/afrikaans_ner_corpus/README.md
@@ -14,7 +14,7 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- structure-prediction
+- token-classification
 task_ids:
 - named-entity-recognition
 paperswithcode_id: null

diff --git a/datasets/air_dialogue/README.md b/datasets/air_dialogue/README.md
@@ -15,12 +15,14 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-- sequence-modeling
+- conversational
+- text-generation
+- fill-mask
 task_ids:
-- conditional-text-generation-other-dialogue-generation
+- dialogue-generation
 - dialogue-modeling
 - language-modeling
+- masked-language-modeling
 paperswithcode_id: null
 ---
 

diff --git a/datasets/allegro_reviews/README.md b/datasets/allegro_reviews/README.md
@@ -14,9 +14,10 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- text-scoring
+- text-classification
 task_ids:
 - sentiment-scoring
+- text-scoring
 paperswithcode_id: allegro-reviews
 pretty_name: Allegro Reviews
 ---

diff --git a/datasets/alt/README.md b/datasets/alt/README.md
@@ -40,10 +40,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-- structure-prediction
+- translation
+- token-classification
 task_ids:
-- machine-translation
 - parsing
 paperswithcode_id: alt
 pretty_name: Asian Language Treebank

diff --git a/datasets/amazon_reviews_multi/README.md b/datasets/amazon_reviews_multi/README.md
@@ -58,15 +58,16 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-- sequence-modeling
+- summarization
+- text-generation
+- fill-mask
 - text-classification
-- text-scoring
 task_ids:
+- text-scoring
 - language-modeling
+- masked-language-modeling
 - sentiment-classification
 - sentiment-scoring
-- summarization
 - topic-classification
 paperswithcode_id: null
 pretty_name: The Multilingual Amazon Reviews Corpus

diff --git a/datasets/ami/README.md b/datasets/ami/README.md
@@ -16,9 +16,8 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- speech-processing
-task_ids:
 - automatic-speech-recognition
+task_ids: []
 ---
 
 # Dataset Card for AMI Corpus

diff --git a/datasets/amttl/README.md b/datasets/amttl/README.md
@@ -14,7 +14,7 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- structure-prediction
+- token-classification
 task_ids:
 - parsing
 paperswithcode_id: null

diff --git a/datasets/app_reviews/README.md b/datasets/app_reviews/README.md
@@ -14,8 +14,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- text-scoring
+- text-classification
 task_ids:
+- text-scoring
 - sentiment-scoring
 paperswithcode_id: null
 pretty_name: AppReviews

diff --git a/datasets/aquamuse/README.md b/datasets/aquamuse/README.md
@@ -20,6 +20,7 @@ source_datasets:
 task_categories:
 - other
 - question-answering
+- text2text-generation
 task_ids:
 - abstractive-qa
 - extractive-qa

diff --git a/datasets/arabic_billion_words/README.md b/datasets/arabic_billion_words/README.md
@@ -33,9 +33,11 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- sequence-modeling
+- text-generation
+- fill-mask
 task_ids:
 - language-modeling
+- masked-language-modeling
 paperswithcode_id: null
 pretty_name: Arabic Billion Words
 ---

diff --git a/datasets/arabic_pos_dialect/README.md b/datasets/arabic_pos_dialect/README.md
@@ -14,7 +14,7 @@ size_categories:
 source_datasets:
 - extended
 task_categories:
-- structure-prediction
+- token-classification
 task_ids:
 - part-of-speech-tagging
 paperswithcode_id: null

diff --git a/datasets/arabic_speech_corpus/README.md b/datasets/arabic_speech_corpus/README.md
@@ -16,9 +16,8 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- speech-processing
-task_ids:
 - automatic-speech-recognition
+task_ids: []
 ---
 
 # Dataset Card for Arabic Speech Corpus

diff --git a/datasets/arxiv_dataset/README.md b/datasets/arxiv_dataset/README.md
@@ -14,15 +14,14 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
+- translation
+- summarization
 - text-retrieval
 task_ids:
 - document-retrieval
 - entity-linking-retrieval
 - explanation-generation
 - fact-checking-retrieval
-- machine-translation
-- summarization
 - text-simplification
 paperswithcode_id: null
 pretty_name: arXiv Dataset

diff --git a/datasets/asset/README.md b/datasets/asset/README.md
@@ -16,12 +16,12 @@ source_datasets:
 - extended|other-turkcorpus
 task_categories:
   ratings:
-  - text-scoring
+  - text-classification
   simplification:
-  - conditional-text-generation
+  - text2text-generation
 task_ids:
   ratings:
-  - text-scoring-other-simplification-evaluation
+  - text-classification-other-simplification-evaluation
   simplification:
   - text-simplification
 paperswithcode_id: asset
@@ -67,7 +67,7 @@ splitting in [HSplit](https://www.aclweb.org/anthology/D18-1081.pdf)), the simpl
 
 ### Supported Tasks and Leaderboards
 
-The dataset supports the evaluation of `test-simplification` systems. Success in this tasks is typically measured using the [SARI](https://huggingface.co/metrics/sari) and [FKBLEU](https://huggingface.co/metrics/fkbleu) metrics described in the paper [Optimizing Statistical Machine Translation for Text Simplification](https://www.aclweb.org/anthology/Q16-1029.pdf).
+The dataset supports the evaluation of `text-simplification` systems. Success in this tasks is typically measured using the [SARI](https://huggingface.co/metrics/sari) and [FKBLEU](https://huggingface.co/metrics/fkbleu) metrics described in the paper [Optimizing Statistical Machine Translation for Text Simplification](https://www.aclweb.org/anthology/Q16-1029.pdf).
 
 ### Languages
 

diff --git a/datasets/assin/README.md b/datasets/assin/README.md
@@ -16,8 +16,8 @@ source_datasets:
 - original
 task_categories:
 - text-classification
-- text-scoring
 task_ids:
+- text-scoring
 - natural-language-inference
 - semantic-similarity-scoring
 paperswithcode_id: assin

diff --git a/datasets/assin2/README.md b/datasets/assin2/README.md
@@ -15,8 +15,8 @@ source_datasets:
 - original
 task_categories:
 - text-classification
-- text-scoring
 task_ids:
+- text-scoring
 - natural-language-inference
 - semantic-similarity-scoring
 paperswithcode_id: assin2

diff --git a/datasets/atomic/README.md b/datasets/atomic/README.md
@@ -15,9 +15,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
+- text2text-generation
 task_ids:
-- other-structured-to-text
+- text2text-generation-other-common-sense-if-then-reasoning
 paperswithcode_id: atomic
 ---
 

diff --git a/datasets/autshumato/README.md b/datasets/autshumato/README.md
@@ -40,9 +40,8 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-task_ids:
-- machine-translation
+- translation
+task_ids: []
 paperswithcode_id: null
 pretty_name: autshumato
 ---

diff --git a/datasets/bbaw_egyptian/README.md b/datasets/bbaw_egyptian/README.md
@@ -16,9 +16,8 @@ size_categories:
 source_datasets:
 - extended|wikipedia
 task_categories:
-- conditional-text-generation
-task_ids:
-- machine-translation
+- translation
+task_ids: []
 paperswithcode_id: null
 pretty_name: BbawEgyptian
 ---

diff --git a/datasets/bc2gm_corpus/README.md b/datasets/bc2gm_corpus/README.md
@@ -14,7 +14,7 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- structure-prediction
+- token-classification
 task_ids:
 - named-entity-recognition
 paperswithcode_id: null

diff --git a/datasets/beans/README.md b/datasets/beans/README.md
@@ -17,7 +17,7 @@ source_datasets:
 task_categories:
 - image-classification
 task_ids:
-- single-label-image-classification
+- multi-class-image-classification
 ---
 
 # Dataset Card for Beans

diff --git a/datasets/best2009/README.md b/datasets/best2009/README.md
@@ -14,9 +14,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- structure-prediction
+- token-classification
 task_ids:
-- structure-prediction-other-word-tokenization
+- token-classification-other-word-tokenization
 paperswithcode_id: null
 pretty_name: best2009
 ---

diff --git a/datasets/bianet/README.md b/datasets/bianet/README.md
@@ -27,9 +27,8 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-task_ids:
-- machine-translation
+- translation
+task_ids: []
 paperswithcode_id: bianet
 pretty_name: Bianet
 ---

diff --git a/datasets/bible_para/README.md b/datasets/bible_para/README.md
@@ -115,9 +115,8 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-task_ids:
-- machine-translation
+- translation
+task_ids: []
 paperswithcode_id: null
 pretty_name: BiblePara
 ---

diff --git a/datasets/big_patent/README.md b/datasets/big_patent/README.md
@@ -33,9 +33,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-task_ids:
 - summarization
+task_ids:
+- summarization-other-patent-summarization
 paperswithcode_id: bigpatent
 pretty_name: Big Patent
 ---

diff --git a/datasets/billsum/README.md b/datasets/billsum/README.md
@@ -14,9 +14,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- conditional-text-generation
-task_ids:
 - summarization
+task_ids:
+- summarization-other-bills-summarization
 paperswithcode_id: billsum
 pretty_name: BillSum
 ---

diff --git a/datasets/biosses/README.md b/datasets/biosses/README.md
@@ -14,8 +14,9 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- text-scoring
+- text-classification
 task_ids:
+- text-scoring
 - semantic-similarity-scoring
 paperswithcode_id: biosses
 pretty_name: BIOSSES

diff --git a/datasets/blbooks/README.md b/datasets/blbooks/README.md
@@ -20,10 +20,12 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- sequence-modeling
+- text-generation
+- fill-mask
 - other
 task_ids:
 - language-modeling
+- masked-language-modeling
 - other-other-digital-humanities-research
 ---
 

diff --git a/datasets/blbooksgenre/README.md b/datasets/blbooksgenre/README.md
@@ -25,11 +25,13 @@ source_datasets:
 - original
 task_categories:
 - text-classification
-- sequence-modeling
+- text-generation
+- fill-mask
 task_ids:
 - topic-classification
 - multi-label-classification
 - language-modeling
+- masked-language-modeling
 ---
 
 # Dataset Card for blbooksgenre

diff --git a/datasets/bnl_newspapers/README.md b/datasets/bnl_newspapers/README.md
@@ -22,9 +22,11 @@ size_categories:
 source_datasets:
 - original
 task_categories:
-- sequence-modeling
+- text-generation
+- fill-mask
 task_ids:
 - language-modeling
+- masked-language-modeling
 ---
 
 # Dataset Card for BnL Historical Newspapers