{"url":"/dataset/ag-news","name":"AG News","full_name":"AG’s News Corpus","description_markdown":"**AG News** (**AG’s News Corpus**) is a subdataset of AG's corpus of news articles constructed by assembling titles and description fields of articles from the 4 largest classes (“World”, “Sports”, “Business”, “Sci/Tech”) of AG’s Corpus. The AG News contains 30,000 training and 1,900 test samples per class.\r\n\r\nSource: [https://arxiv.org/pdf/1509.01626.pdf](https://arxiv.org/pdf/1509.01626.pdf)","description_withheld":null,"homepage":"http://groups.di.unipi.it/~gulli/AG_corpus_of_news_articles.html","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/character-level-convolutional-networks-for","title":"Character-level Convolutional Networks for Text Classification","first_author":"Xiang Zhang","url":null},"license":{"name":"Custom (non-commercial)","url":"http://groups.di.unipi.it/~gulli/AG_corpus_of_news_articles.html"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"},{"name":"Stochastic Optimization","url":"/task/stochastic-optimization","datasets_with_task":"/datasets/task/stochastic-optimization"},{"name":"Topic Models","url":"/task/topic-models","datasets_with_task":"/datasets/task/topic-models"},{"name":"Short Text Clustering","url":"/task/short-text-clustering","datasets_with_task":"/datasets/task/short-text-clustering"},{"name":"Unsupervised Text Classification","url":"/task/unsupervised-text-classification","datasets_with_task":"/datasets/task/unsupervised-text-classification"},{"name":"Continual Pretraining","url":"/task/continual-pretraining","datasets_with_task":"/datasets/task/continual-pretraining"},{"name":"Zero-Shot Text Classification","url":"/task/zero-shot-text-classification","datasets_with_task":"/datasets/task/zero-shot-text-classification"},{"name":"Semi-Supervised Text Classification","url":"/task/semi-supervised-text-classification-1","datasets_with_task":"/datasets/task/semi-supervised-text-classification-1"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["AG News","AG News (200 Labels)","ag_news"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wangrongsheng/ag_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KETI-AIR/kor_ag_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fancyzhx/ag_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ag_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pietrolesci/ag_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KETI-AIR/ag_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/ag_news_subset","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/text","url":"https://pytorch.org/text/stable/datasets.html#torchtext.datasets.AG_NEWS","frameworks":["pytorch"]}],"num_papers_in_archive":969,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-ag-news","task":"Text Classification","dataset_variant":"AG News","rows":24,"metrics":["Error"],"first_row_in_archive_order":{"model":"XLNet","paper":"/paper/xlnet-generalized-autoregressive-pretraining","metrics":{"Error":"4.45"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/topic-models-on-ag-news","task":"Topic Models","dataset_variant":"AG News","rows":6,"metrics":["C_v","NPMI"],"first_row_in_archive_order":{"model":"vONTSS","paper":"/paper/vontss-vmf-based-semi-supervised-neural-topic","metrics":{"C_v":"0.49","NPMI":"0.054"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-text-classification-on-ag-1","task":"Semi-Supervised Text Classification","dataset_variant":"AG News (200 Labels)","rows":3,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"FlowGMM","paper":"/paper/semi-supervised-learning-with-normalizing-1","metrics":{"Accuracy (%)":"82.1"},"code_links":[{"title":"izmailovpavel/flowgmm","url":"https://github.com/izmailovpavel/flowgmm"},{"title":"sadrasafa/FlowGMM-Julia","url":"https://github.com/sadrasafa/FlowGMM-Julia"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-text-classification-on-ag-news","task":"Unsupervised Text Classification","dataset_variant":"AG News","rows":2,"metrics":["F1 score","F1-score"],"first_row_in_archive_order":{"model":"Lbl2Vec","paper":"/paper/lbl2vec-an-embedding-based-approach-for","metrics":{"F1 score":"82.7"},"code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/anomaly-detection-on-ag-news","task":"Anomaly Detection","dataset_variant":"AG News","rows":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"DATE","paper":"/paper/date-detecting-anomalies-in-text-via-self","metrics":{"AUROC":"90"},"code_links":[{"title":"bit-ml/date","url":"https://github.com/bit-ml/date"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/continual-pretraining-on-ag-news","task":"Continual Pretraining","dataset_variant":"AG News","rows":1,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"CPT","paper":"/paper/continual-training-of-language-models-for-few","metrics":{"F1 - macro":"63.77"},"code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"},{"title":"UIC-Liu-Lab/ContinualLM","url":"https://github.com/UIC-Liu-Lab/ContinualLM"},{"title":"uic-liu-lab/cpt","url":"https://github.com/uic-liu-lab/cpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/short-text-clustering-on-ag-news","task":"Short Text Clustering","dataset_variant":"AG News","rows":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper":"/paper/supporting-clustering-with-contrastive","metrics":{"Acc":"88.2"},"code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/stochastic-optimization-on-ag-news","task":"Stochastic Optimization","dataset_variant":"AG News","rows":1,"metrics":["Accuracy (max)","Accuracy (mean)"],"first_row_in_archive_order":{"model":"Bert","paper":"/paper/mixing-adam-and-sgd-a-combined-optimization","metrics":{"Accuracy (max)":"93.99","Accuracy (mean)":"93.86"},"code_links":[{"title":"nicolalandro/multi_optimizer","url":"https://gitlab.com/nicolalandro/multi_optimizer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-ag-news-1","task":"Text Classification","dataset_variant":"ag_news","rows":0,"metrics":["Accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/capo-cost-aware-prompt-optimization","title":"CAPO: Cost-Aware Prompt Optimization","date":"2025-04-22","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/vontss-vmf-based-semi-supervised-neural-topic","title":"vONTSS: vMF based semi-supervised neural topic modeling with optimal transport","date":"2023-07-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","date":"2022-11-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/lbl2vec-an-embedding-based-approach-for","title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","date":"2022-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/continual-training-of-language-models-for-few","title":"Continual Training of Language Models for Few-Shot Learning","date":"2022-10-11","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/date-detecting-anomalies-in-text-via-self","title":"DATE: Detecting Anomalies in Text via Self-Supervision of Transformers","date":"2021-04-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/supporting-clustering-with-contrastive","title":"Supporting Clustering with Contrastive Learning","date":"2021-03-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mixing-adam-and-sgd-a-combined-optimization","title":"Mixing ADAM and SGD: a Combined Optimization Method","date":"2020-11-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revisiting-lstm-networks-for-semi-supervised-1","title":"Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function","date":"2020-09-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-sinkhorn-topic-model","title":"Neural Topic Model via Optimal Transport","date":"2020-08-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-learning-with-normalizing-1","title":"Semi-Supervised Learning with Normalizing Flows","date":"2019-12-30","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sampling-bias-in-deep-active-classification","title":"Sampling Bias in Deep Active Classification: An Empirical Study","date":"2019-09-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/topic-modeling-in-embedding-spaces","title":"Topic Modeling in Embedding Spaces","date":"2019-07-08","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":3,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":10,"samples_unverified":14,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/how-to-fine-tune-bert-for-text-classification","title":"How to Fine-Tune BERT for Text Classification?","date":"2019-05-14","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":6,"samples_unverified":12,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/squeezed-very-deep-convolutional-neural","title":"Squeezed Very Deep Convolutional Neural Networks for Text Classification","date":"2019-01-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-to-remember-more-with-less","title":"Learning to Remember More with Less Memorization","date":"2019-01-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/explicit-interaction-model-towards-text","title":"Explicit Interaction Model towards Text Classification","date":"2018-11-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/compositional-coding-capsule-network-with-k","title":"Compositional Coding Capsule Network with K-Means Routing for Text Classification","date":"2018-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spherical-latent-spaces-for-stable","title":"Spherical Latent Spaces for Stable Variational Autoencoders","date":"2018-08-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/on-tree-based-neural-sentence-modeling","title":"On Tree-Based Neural Sentence Modeling","date":"2018-08-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/task-oriented-word-embedding-for-text","title":"Task-oriented Word Embedding for Text Classification","date":"2018-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disconnected-recurrent-neural-networks-for","title":"Disconnected Recurrent Neural Networks for Text Categorization","date":"2018-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/abstractive-text-classification-using","title":"Abstractive Text Classification Using Sequence-to-convolution Neural Networks","date":"2018-05-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-embedding-of-words-and-labels-for-text","title":"Joint Embedding of Words and Labels for Text Classification","date":"2018-05-10","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/investigating-capsule-networks-with-dynamic","title":"Investigating Capsule Networks with Dynamic Routing for Text Classification","date":"2018-03-29","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/universal-language-model-fine-tuning-for-text","title":"Universal Language Model Fine-tuning for Text Classification","date":"2018-01-18","rows_on_this_dataset":1,"code_links":66,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-pyramid-convolutional-neural-networks","title":"Deep Pyramid Convolutional Neural Networks for Text Categorization","date":"2017-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/discovering-discrete-latent-topics-with","title":"Discovering Discrete Latent Topics with Neural Variational Inference","date":"2017-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/autoencoding-variational-inference-for-topic","title":"Autoencoding Variational Inference For Topic Models","date":"2017-03-04","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bag-of-tricks-for-efficient-text","title":"Bag of Tricks for Efficient Text Classification","date":"2016-07-06","rows_on_this_dataset":1,"code_links":65,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/very-deep-convolutional-networks-for-text","title":"Very Deep Convolutional Networks for Text Classification","date":"2016-06-06","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/supervised-and-semi-supervised-text","title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","date":"2016-02-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/character-level-convolutional-networks-for","title":"Character-level Convolutional Networks for Text Classification","date":"2015-09-04","rows_on_this_dataset":1,"code_links":30,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":4,"samples_unverified":16,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":17,"samples_harvested":127,"samples_ran":41,"samples_unverified":86,"pointer_only_for_licence":31,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}