{"url":"/dataset/m3ls-multi-lingual-multi-modal-summarization","name":"M3LS","full_name":"Multi-Lingual Multi-Modal Summarization Dataset","description_markdown":"Significant developments in techniques such as encoder-decoder models have enabled us to represent information comprising multiple modalities. This information can further enhance many downstream tasks in the field of information retrieval and natural language processing; however, improvements in multi-modal techniques and their performance evaluation require large-scale multi-modal data which offers sufficient diversity. Multi-lingual modeling for a variety of tasks like multi-modal summarization, text generation, and translation leverages information derived from high-quality multi-lingual annotated data. In this work, we present the current largest multi-lingual multi-modal summarization dataset (M3LS), and it consists of over a million instances of document-image pairs along with a professionally annotated multi-modal summary for each pair. It is derived from news articles published by British Broadcasting Corporation(BBC) over a decade and spans 20 languages, targeting diversity across five language roots, it is also the largest summarization dataset for 13 languages and consists of cross-lingual summarization data for 2 languages. We formally define the multi-lingual multi-modal summarization task utilizing our dataset and report baseline scores from various state-of-the-art summarization techniques in a multi-lingual setting. We also compare it with many similar datasets to analyze the uniqueness and difficulty of M3LS.","description_withheld":null,"homepage":"https://github.com/zenquiorra/M3LS","introduced_date":"2023-02-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-multi-lingual-multi-modal","title":"Large Scale Multi-Lingual Multi-Modal Summarization Dataset","first_author":"Yash Verma","url":null},"license":{"name":"MIT","url":"https://github.com/zenquiorra/M3LS/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Cross-Lingual Abstractive Summarization","url":"/task/cross-lingual-abstractive-summarization","datasets_with_task":"/datasets/task/cross-lingual-abstractive-summarization"},{"name":"Multimodal Abstractive Text Summarization","url":"/task/multimodal-abstractive-text-summarization","datasets_with_task":"/datasets/task/multimodal-abstractive-text-summarization"},{"name":"Cross-Language Text Summarization","url":"/task/cross-language-text-summarization","datasets_with_task":"/datasets/task/cross-language-text-summarization"},{"name":"Data Summarization","url":"/task/data-summarization","datasets_with_task":"/datasets/task/data-summarization"},{"name":"News Summarization","url":"/task/news-summarization","datasets_with_task":"/datasets/task/news-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"},{"name":"Urdu","url":"/datasets/language/urdu"},{"name":"Gujarati","url":"/datasets/language/gujarati"},{"name":"Nepali (individual language)","url":"/datasets/language/nepali-individual-language"},{"name":"Punjabi","url":"/datasets/language/punjabi"},{"name":"Southern Pashto","url":"/datasets/language/southern-pashto"},{"name":"Sinhala","url":"/datasets/language/sinhala"}],"variants":["M3LS"],"data_loaders":[{"repo":"https://github.com/zenquiorra/m3ls","url":"https://github.com/zenquiorra/m3ls","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}