{"url":"/dataset/cnn-daily-mail-1","name":"CNN/Daily Mail","full_name":"CNN/Daily Mail","description_markdown":"**CNN/Daily Mail** is a dataset for text summarization. Human generated abstractive summary bullets were generated from news stories in CNN and Daily Mail websites as questions (with one of the entities hidden), and stories as the corresponding passages from which the system is expected to answer the fill-in the-blank question. The authors released the scripts that crawl, extract and generate pairs of passages and questions from these websites.\r\n\r\nIn all, the corpus has 286,817 training pairs, 13,368 validation pairs and 11,487 test pairs, as defined by their scripts. The source documents in the training set have 766 words spanning 29.74 sentences on an average while the summaries consist of 53 words and 3.72 sentences. \r\n\r\nSource: [Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond](https://arxiv.org/pdf/1602.06023v5.pdf)","description_withheld":null,"homepage":"https://github.com/abisee/cnn-dailymail","introduced_date":"2016-08-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/abstractive-text-summarization-using-sequence","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","first_author":"Ramesh Nallapati","url":null},"license":{"name":"MIT","url":"https://github.com/abisee/cnn-dailymail"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Sequence-to-sequence Language Modeling","url":"/task/sequence-to-sequence-language-modeling","datasets_with_task":"/datasets/task/sequence-to-sequence-language-modeling"},{"name":"Document Summarization","url":"/task/document-summarization","datasets_with_task":"/datasets/task/document-summarization"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"},{"name":"Extractive Text Summarization","url":"/task/extractive-document-summarization","datasets_with_task":"/datasets/task/extractive-document-summarization"},{"name":"Extractive Document Summarization","url":"/task/extractive-document-summarization-1","datasets_with_task":"/datasets/task/extractive-document-summarization-1"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ml6team/cnn_dailymail_nl","cnn_dailymail 3.0.0","yhavinga/cnn_dailymail_dutch","cnn_dailymail","CNN / Daily Mail (Anonymized)","CNN-DM","CNN / Daily Mail","CNN/Daily Mail"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/behind-the-cmo/behind-the-cmo-newsletter","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cnn_dailymail","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/samyakmohelay/genai_dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ZhongshengWang/Alpaca-cnn-dailymail","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/abisee/cnn_dailymail","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/texta1564/smart_sentry","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ccdv/cnn_dailymail","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/malteos/test2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nbroad/citesum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/biglam/atypical_animacy","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/elihoole/asrs-aviation-reports","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/yhavinga/cnn_dailymail_dutch","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#cnn/dm-summarisation","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/cnn_dailymail","frameworks":["tf","jax"]},{"repo":"https://github.com/abisee/cnn-dailymail","url":"https://github.com/abisee/cnn-dailymail","frameworks":["tf"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/generation/dataset_readers/cnn_dm/","frameworks":["pytorch"]}],"num_papers_in_archive":530,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily","task":"Abstractive Text Summarization","dataset_variant":"CNN / Daily Mail","rows":53,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"Scrambled code + broken (alter)","paper":"/paper/universal-evasion-attacks-on-summarization","metrics":{"ROUGE-1":"48.18","ROUGE-2":"19.84","ROUGE-L":"45.35"},"code_links":[{"title":"cestwc/universal-evasion","url":"https://github.com/cestwc/universal-evasion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","task":"Document Summarization","dataset_variant":"CNN / Daily Mail","rows":26,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","PPL"],"first_row_in_archive_order":{"model":"Scrambled code + broken (alter)","paper":"/paper/universal-evasion-attacks-on-summarization","metrics":{"ROUGE-1":"48.18","ROUGE-2":"19.84","ROUGE-L":"45.35"},"code_links":[{"title":"cestwc/universal-evasion","url":"https://github.com/cestwc/universal-evasion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-cnn-daily-mail","task":"Question Answering","dataset_variant":"CNN / Daily Mail","rows":16,"metrics":["CNN","Daily Mail"],"first_row_in_archive_order":{"model":"GA+MAGE (32)","paper":"/paper/linguistic-knowledge-as-memory-for-recurrent","metrics":{"CNN":"78.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/extractive-document-summarization-on-cnn","task":"Extractive Text Summarization","dataset_variant":"CNN / Daily Mail","rows":15,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"HAHSum","paper":"/paper/neural-extractive-summarization-with","metrics":{"ROUGE-1":"44.68","ROUGE-2":"21.30","ROUGE-L":"40.75"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-summarization-on-cnn-daily-mail-2","task":"Text Summarization","dataset_variant":"CNN / Daily Mail (Anonymized)","rows":13,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"HSSAS","paper":"/paper/a-hierarchical-structured-self-attentive","metrics":{"ROUGE-1":"42.3","ROUGE-2":"17.8","ROUGE-L":"37.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily-2","task":"Abstractive Text Summarization","dataset_variant":"CNN/Daily Mail","rows":4,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper":"/paper/textbox-2-0-a-text-generation-library-with","metrics":{"ROUGE-1":"44.47","ROUGE-2":"21.5","ROUGE-L":"41.35"},"code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-cnn-daily-mail","task":"Text Generation","dataset_variant":"CNN/Daily Mail","rows":1,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"PALM","paper":"/paper/palm-pre-training-an-autoencoding","metrics":{"ROUGE-L":"41.41"},"code_links":[{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind/tree/main/PALM"},{"title":"overwindows/PALM","url":"https://github.com/overwindows/PALM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/summarization-on-cnn-dailymail","task":"Summarization","dataset_variant":"cnn_dailymail","rows":0,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","ROUGE-LSUM","gen_len","loss"],"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/salient-information-prompting-to-steer","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","date":"2024-10-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/segmented-recurrent-transformer-an-efficient","title":"Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model","date":"2023-05-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fourier-transformer-fast-long-range-modeling","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","date":"2023-05-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/align-and-attend-multimodal-summarization","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","date":"2023-03-13","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","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/universal-evasion-attacks-on-summarization","title":"Universal Evasion Attacks on Summarization Scoring","date":"2022-10-25","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/salience-allocation-as-guidance-for","title":"Salience Allocation as Guidance for Abstractive Summarization","date":"2022-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/calibrating-sequence-likelihood-improves","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","date":"2022-09-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/brio-bringing-order-to-abstractive","title":"BRIO: Bringing Order to Abstractive Summarization","date":"2022-03-31","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/summareranker-a-multi-task-mixture-of-experts-1","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","date":"2022-03-13","rows_on_this_dataset":2,"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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/longt5-efficient-text-to-text-transformer-for","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","date":"2021-12-15","rows_on_this_dataset":1,"code_links":4,"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/learn-to-copy-from-the-copying-history","title":"Learn to Copy from the Copying History: Correlational Copy Network for Abstractive Summarization","date":"2021-11-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/considering-nested-tree-structure-in-sentence","title":"Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer","date":"2021-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fastformer-additive-attention-is-all-you-need","title":"Fastformer: Additive Attention Can Be All You Need","date":"2021-08-20","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/r-drop-regularized-dropout-for-neural","title":"R-Drop: Regularized Dropout for Neural Networks","date":"2021-06-28","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simcls-a-simple-framework-for-contrastive","title":"SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization","date":"2021-06-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-abstractive-summarization-with-1","title":"IMPROVING ABSTRACTIVE SUMMARIZATION WITH SEGMENT-AUGMENTED AND POSITION-AWARENESS (ACLing2021)","date":"2021-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hie-bart-document-summarization-with","title":"Hie-BART: Document Summarization with Hierarchical BART","date":"2021-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-summary-loop-learning-to-write-1","title":"The Summary Loop: Learning to Write Abstractive Summaries Without Examples","date":"2021-05-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-learning-for-generation-with","title":"Hierarchical Learning for Generation with Long Source Sequences","date":"2021-04-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mask-attention-networks-rethinking-and","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","date":"2021-03-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","rows_on_this_dataset":2,"code_links":8,"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/muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/subformer-a-parameter-reduced-transformer","title":"Subformer: A Parameter Reduced Transformer","date":"2021-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-extractive-summarization-with","title":"Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network","date":"2020-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/better-fine-tuning-by-reducing","title":"Better Fine-Tuning by Reducing Representational Collapse","date":"2020-08-06","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":10,"samples_unverified":5,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/synthesizer-rethinking-self-attention-in","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","date":"2020-05-02","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/extractive-summarization-as-text-matching","title":"Extractive Summarization as Text Matching","date":"2020-04-19","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/palm-pre-training-an-autoencoding","title":"PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation","date":"2020-04-14","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/unilmv2-pseudo-masked-language-models-for","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-02-28","rows_on_this_dataset":1,"code_links":3,"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/time-aware-large-kernel-convolutions","title":"Time-aware Large Kernel Convolutions","date":"2020-02-08","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","date":"2020-01-26","rows_on_this_dataset":3,"code_links":5,"syntology":null},{"paper":"/paper/prophetnet-predicting-future-n-gram-for","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","date":"2020-01-13","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/pegasus-pre-training-with-extracted-gap","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","date":"2019-12-18","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":1,"samples_unverified":18,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reading-like-her-human-reading-inspired","title":"Reading Like HER: Human Reading Inspired Extractive Summarization","date":"2019-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":53,"samples_ran":22,"samples_unverified":31,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","rows_on_this_dataset":2,"code_links":57,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":2,"samples_unverified":29,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mixture-content-selection-for-diverse","title":"Mixture Content Selection for Diverse Sequence Generation","date":"2019-09-04","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","rows_on_this_dataset":2,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":7,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/delta-a-deep-learning-based-language","title":"DELTA: A DEep learning based Language Technology plAtform","date":"2019-08-02","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/searching-for-effective-neural-extractive","title":"Searching for Effective Neural Extractive Summarization: What Works and What's Next","date":"2019-07-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/hibert-document-level-pre-training-of","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","date":"2019-05-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","rows_on_this_dataset":2,"code_links":9,"syntology":null},{"paper":"/paper/fine-tune-bert-for-extractive-summarization","title":"Fine-tune BERT for Extractive Summarization","date":"2019-03-25","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-editorial-network-for-enhanced-document","title":"An Editorial Network for Enhanced Document Summarization","date":"2019-02-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pretraining-based-natural-language-generation","title":"Pretraining-Based Natural Language Generation for Text Summarization","date":"2019-02-25","rows_on_this_dataset":1,"code_links":4,"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/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/pay-less-attention-with-lightweight-and","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","date":"2019-01-29","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/improving-neural-abstractive-document-1","title":"Improving Neural Abstractive Document Summarization with Structural Regularization","date":"2018-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-neural-abstractive-document","title":"Improving Neural Abstractive Document Summarization with Explicit Information Selection Modeling","date":"2018-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/iterative-document-representation-learning","title":"Iterative Document Representation Learning Towards Summarization with Polishing","date":"2018-09-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/banditsum-extractive-summarization-as-a","title":"BanditSum: Extractive Summarization as a Contextual Bandit","date":"2018-09-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/closed-book-training-to-improve-summarization","title":"Closed-Book Training to Improve Summarization Encoder Memory","date":"2018-09-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bottom-up-abstractive-summarization","title":"Bottom-Up Abstractive Summarization","date":"2018-08-31","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-abstraction-in-text-summarization","title":"Improving Abstraction in Text Summarization","date":"2018-08-23","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/neural-latent-extractive-document","title":"Neural Latent Extractive Document Summarization","date":"2018-08-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-document-summarization-by-jointly","title":"Neural Document Summarization by Jointly Learning to Score and Select Sentences","date":"2018-07-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/extractive-summarization-with-swap-net","title":"Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks","date":"2018-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/guiding-generation-for-abstractive-text","title":"Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network","date":"2018-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/soft-layer-specific-multi-task-summarization","title":"Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation","date":"2018-05-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fast-abstractive-summarization-with-reinforce","title":"Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting","date":"2018-05-28","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-hierarchical-structured-self-attentive","title":"A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)","date":"2018-05-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-unified-model-for-extractive-and","title":"A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss","date":"2018-05-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-extract-coherent-summary-via-deep","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","date":"2018-04-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-reward-reinforced-summarization-with","title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","date":"2018-04-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-communicating-agents-for-abstractive","title":"Deep Communicating Agents for Abstractive Summarization","date":"2018-03-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ranking-sentences-for-extractive","title":"Ranking Sentences for Extractive Summarization with Reinforcement Learning","date":"2018-02-23","rows_on_this_dataset":1,"code_links":1,"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/generative-adversarial-network-for","title":"Generative Adversarial Network for Abstractive Text Summarization","date":"2017-11-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-attention-models-for-document","title":"Coarse-to-Fine Attention Models for Document Summarization","date":"2017-09-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/abstractive-document-summarization-with-a","title":"Abstractive Document Summarization with a Graph-Based Attentional Neural Model","date":"2017-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","rows_on_this_dataset":1,"code_links":595,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":946,"samples_ran":600,"samples_unverified":346,"pointer_only_for_licence":451,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-deep-reinforced-model-for-abstractive","title":"A Deep Reinforced Model for Abstractive Summarization","date":"2017-05-11","rows_on_this_dataset":3,"code_links":10,"syntology":null},{"paper":"/paper/get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","rows_on_this_dataset":5,"code_links":39,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":64,"samples_ran":30,"samples_unverified":34,"pointer_only_for_licence":44,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/linguistic-knowledge-as-memory-for-recurrent","title":"Linguistic Knowledge as Memory for Recurrent Neural Networks","date":"2017-03-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/summarunner-a-recurrent-neural-network-based","title":"SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents","date":"2016-11-14","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reasonet-learning-to-stop-reading-in-machine","title":"ReasoNet: Learning to Stop Reading in Machine Comprehension","date":"2016-09-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/attention-over-attention-neural-networks-for","title":"Attention-over-Attention Neural Networks for Reading Comprehension","date":"2016-07-15","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-thorough-examination-of-the-cnndaily-mail","title":"A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task","date":"2016-06-09","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/natural-language-comprehension-with-the","title":"Natural Language Comprehension with the EpiReader","date":"2016-06-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/iterative-alternating-neural-attention-for","title":"Iterative Alternating Neural Attention for Machine Reading","date":"2016-06-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gated-attention-readers-for-text","title":"Gated-Attention Readers for Text Comprehension","date":"2016-06-05","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynamic-entity-representation-with-max","title":"Dynamic Entity Representation with Max-pooling Improves Machine Reading","date":"2016-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/text-understanding-with-the-attention-sum","title":"Text Understanding with the Attention Sum Reader Network","date":"2016-03-04","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/abstractive-text-summarization-using-sequence","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","date":"2016-02-19","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/teaching-machines-to-read-and-comprehend","title":"Teaching Machines to Read and Comprehend","date":"2015-06-10","rows_on_this_dataset":3,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"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":31,"samples_harvested":1255,"samples_ran":720,"samples_unverified":535,"pointer_only_for_licence":528,"papers_with_no_sample_that_ran":6,"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."}