{"url":"/task/multi-modal-named-entity-recognition","name":"Multi-modal Named Entity Recognition","slug":"multi-modal-named-entity-recognition","description_markdown":"Multi-modal named entity recognition aims at improving\r\nthe accuracy of NER models through utilizing image information.","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":"derived"},"counts":{"papers_tagged":10,"papers_with_code":6,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-modal-named-entity-recognition-on","slug":"multi-modal-named-entity-recognition-on","dataset":"Twitter-15","dataset_url":null,"rows_in_archive":6,"metrics":["F1"],"first_row_in_archive_order":{"model":"PGIM","paper_title":"Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge","paper_url":"/paper/prompt-chatgpt-in-mner-improved-multimodal","paper_date":"2023-05-20","arxiv_id":"2305.12212","code_links":[{"title":"jinyuanli0012/pgim","url":"https://github.com/jinyuanli0012/pgim"}],"syntology":null}},{"leaderboard":"/sota/multi-modal-named-entity-recognition-on-snap","slug":"multi-modal-named-entity-recognition-on-snap","dataset":"SNAP (MNER)","dataset_url":null,"rows_in_archive":6,"metrics":["F1"],"first_row_in_archive_order":{"model":"MoRe-MoE","paper_title":"Named Entity and Relation Extraction with Multi-Modal Retrieval","paper_url":"/paper/named-entity-and-relation-extraction-with","paper_date":"2022-12-03","arxiv_id":"2212.01612","code_links":[{"title":"modelscope/adaseq","url":"https://github.com/modelscope/adaseq"}],"syntology":null}},{"leaderboard":"/sota/multi-modal-named-entity-recognition-on-2","slug":"multi-modal-named-entity-recognition-on-2","dataset":"WikiDiverse","dataset_url":null,"rows_in_archive":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"MoRe-MoE","paper_title":"Named Entity and Relation Extraction with Multi-Modal Retrieval","paper_url":"/paper/named-entity-and-relation-extraction-with","paper_date":"2022-12-03","arxiv_id":"2212.01612","code_links":[{"title":"modelscope/adaseq","url":"https://github.com/modelscope/adaseq"}],"syntology":null}},{"leaderboard":"/sota/multi-modal-named-entity-recognition-on-3","slug":"multi-modal-named-entity-recognition-on-3","dataset":"Twitter-2017","dataset_url":null,"rows_in_archive":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"PGIM","paper_title":"Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge","paper_url":"/paper/prompt-chatgpt-in-mner-improved-multimodal","paper_date":"2023-05-20","arxiv_id":"2305.12212","code_links":[{"title":"jinyuanli0012/pgim","url":"https://github.com/jinyuanli0012/pgim"}],"syntology":null}},{"leaderboard":"/sota/multi-modal-named-entity-recognition-on-1","slug":"multi-modal-named-entity-recognition-on-1","dataset":"Twitter-17","dataset_url":null,"rows_in_archive":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"ITA-All","paper_title":"ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition","paper_url":"/paper/ita-image-text-alignments-for-multi-modal","paper_date":"2021-12-13","arxiv_id":"2112.06482","code_links":[{"title":"alibaba-nlp/kb-ner","url":"https://github.com/alibaba-nlp/kb-ner"}],"syntology":null}}],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)"}],"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":6,"of":6,"tagged_in_all":10,"items":[{"url":"/paper/llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","repositories_listed":2,"syntology":null},{"url":"/paper/prompt-chatgpt-in-mner-improved-multimodal","title":"Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge","date":"2023-05-20","arxiv_id":"2305.12212","repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-and-relation-extraction-with","title":"Named Entity and Relation Extraction with Multi-Modal Retrieval","date":"2022-12-03","arxiv_id":"2212.01612","repositories_listed":1,"syntology":null},{"url":"/paper/ita-image-text-alignments-for-multi-modal","title":"ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition","date":"2021-12-13","arxiv_id":"2112.06482","repositories_listed":1,"syntology":null},{"url":"/paper/rpbert-a-text-image-relation-propagation","title":"RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER","date":"2021-02-05","arxiv_id":"2102.02967","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multimodal-named-entity-recognition","title":"Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer","date":"2020-07-01","arxiv_id":null,"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"}}