{"url":"/sota/multi-modal-named-entity-recognition-on-3","task":{"name":"Multi-modal Named Entity Recognition","url":"/task/multi-modal-named-entity-recognition","note":null},"dataset":{"name":"Twitter-2017","url":null},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Multi-modal named entity recognition aims at improving\r\nthe accuracy of NER models through utilizing image information.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"PGIM","metrics":{"F1":"91.43"},"uses_additional_data":true,"paper_date":"2023-05-20","paper":"/paper/prompt-chatgpt-in-mner-improved-multimodal","paper_url":"https://arxiv.org/abs/2305.12212v2","paper_title":"Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge","code":"https://github.com/jinyuanli0012/pgim","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MoRe-MoE","metrics":{"F1":"90.67"},"uses_additional_data":false,"paper_date":"2022-12-03","paper":"/paper/named-entity-and-relation-extraction-with","paper_url":"https://arxiv.org/abs/2212.01612v1","paper_title":"Named Entity and Relation Extraction with Multi-Modal Retrieval","code":"https://github.com/modelscope/adaseq","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ITA-All","metrics":{"F1":"89.75"},"uses_additional_data":false,"paper_date":"2021-12-13","paper":"/paper/ita-image-text-alignments-for-multi-modal","paper_url":"https://arxiv.org/abs/2112.06482v4","paper_title":"ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition","code":"https://github.com/alibaba-nlp/kb-ner","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}