{"url":"/task/multimodal-abstractive-text-summarization","name":"Multimodal Abstractive Text Summarization","slug":"multimodal-abstractive-text-summarization","description_markdown":"Abstractive text summarization by utilizing information from multiple modalities.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2,"papers_with_code":2,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multimodal-abstractive-text-summarization-on","slug":"multimodal-abstractive-text-summarization-on","dataset":"How2 300h","dataset_url":"/dataset/how2","rows_in_archive":1,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"MAST","paper_title":"MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention","paper_url":"/paper/mast-multimodal-abstractive-summarization","paper_date":"2020-10-15","arxiv_id":"2010.08021","code_links":[{"title":"amankhullar/mast","url":"https://github.com/amankhullar/mast"}],"syntology":null}}],"datasets":[{"url":"/dataset/how2","name":"How2","full_name":"","num_papers_in_archive":84},{"url":"/dataset/findsum","name":"FINDSum","full_name":"Financial Report Document Summarization","num_papers_in_archive":2},{"url":"/dataset/m3ls-multi-lingual-multi-modal-summarization","name":"M3LS","full_name":"Multi-Lingual Multi-Modal Summarization Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":2,"items":[{"url":"/paper/long-text-and-multi-table-summarization","title":"Long Text and Multi-Table Summarization: Dataset and Method","date":"2023-02-08","arxiv_id":"2302.03815","repositories_listed":1,"syntology":null},{"url":"/paper/mast-multimodal-abstractive-summarization","title":"MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention","date":"2020-10-15","arxiv_id":"2010.08021","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}