{"url":"/dataset/samsum-corpus","name":"SAMSum","full_name":null,"description_markdown":"A new dataset with abstractive dialogue summaries.\r\n\r\nSource: [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](/paper/samsum-corpus-a-human-annotated-dialogue-1)","description_withheld":null,"homepage":"https://arxiv.org/src/1911.12237v2/anc","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/samsum-corpus-a-human-annotated-dialogue-1","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","first_author":"Bogdan Gliwa","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"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":"Federated Learning","url":"/task/federated-learning","datasets_with_task":"/datasets/task/federated-learning"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"},{"name":"dialogue summary","url":"/task/dialogue-summary","datasets_with_task":"/datasets/task/dialogue-summary"},{"name":"Abstractive Dialogue Summarization","url":"/task/abstractive-dialogue-summarization","datasets_with_task":"/datasets/task/abstractive-dialogue-summarization"}],"languages":[],"variants":["SAMSum","SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","SAMSum Corpus (translated to Russian)"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Samsung/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/supermario/dt-random-2.3","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/knkarthick/xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/knkarthick/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fiellin/abcdsamsumid","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fiellin/abcsamsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Axel578/mydt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hopkiz/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/samsum","frameworks":["tf","jax"]}],"num_papers_in_archive":145,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-samsum-corpus","task":"Text Summarization","dataset_variant":"SAMSum","rows":12,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","BertScoreF1"],"first_row_in_archive_order":{"model":"OmniVec2","paper":"/paper/omnivec2-a-novel-transformer-based-network","metrics":{"BertScoreF1":"65.1","ROUGE-1":"59.1","ROUGE-2":"34.1","ROUGE-L":"63.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/abstractive-text-summarization-on-samsum","task":"Abstractive Text Summarization","dataset_variant":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","rows":0,"metrics":["Test ROUGE-1","Test ROUGE-2","Test ROUGE-L","Validation ROUGE-1","Validation ROUGE-2","Validation ROUGE-L"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/summarization-on-samsum-1","task":"Summarization","dataset_variant":"SAMSum","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"},{"leaderboard":"/sota/summarization-on-samsum-corpus-a-human","task":"Summarization","dataset_variant":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","rows":0,"metrics":["Test ROGUE-1","Test ROGUE-2","Test ROGUE-L","Validation ROGUE-1","Validation ROGUE-2","Validation ROGUE-L"],"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":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-prompting-taxonomy-a-universal","title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","date":"2024-06-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/instructive-dialogue-summarization-with-query","title":"Instructive Dialogue Summarization with Query Aggregations","date":"2023-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/momentum-calibration-for-text-generation","title":"Momentum Calibration for Text Generation","date":"2022-12-08","rows_on_this_dataset":1,"code_links":0,"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/mind-the-gap-injecting-commonsense-knowledge","title":"Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization","date":"2022-09-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/topic-aware-contrastive-learning-for","title":"Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization","date":"2021-09-10","rows_on_this_dataset":2,"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":2,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}