{"url":"/task/named-entity-recognition","name":"named-entity-recognition","slug":"named-entity-recognition","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2491,"papers_with_code":908,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/nuner","name":"NuNER","full_name":"","num_papers_in_archive":4},{"url":"/dataset/somd","name":"SOMD","full_name":"SOftware Mention Detection","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":30,"of":908,"tagged_in_all":2491,"items":[{"url":"/paper/nezha-neural-contextualized-representation","title":"NEZHA: Neural Contextualized Representation for Chinese Language Understanding","date":"2019-08-31","arxiv_id":"1909.00204","repositories_listed":10,"syntology":null},{"url":"/paper/crossner-evaluating-cross-domain-named-entity","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","date":"2020-12-08","arxiv_id":"2012.04373","repositories_listed":5,"syntology":null},{"url":"/paper/klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","date":"2021-05-20","arxiv_id":"2105.09680","repositories_listed":4,"syntology":null},{"url":"/paper/arabert-transformer-based-model-for-arabic","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","date":"2020-02-28","arxiv_id":"2003.00104","repositories_listed":4,"syntology":null},{"url":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/entity-relation-and-event-extraction-with","title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","date":"2019-09-08","arxiv_id":"1909.03546","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/rita-automatic-framework-for-designing-of","title":"RITA: Automatic Framework for Designing of Resilient IoT Applications","date":"2024-11-27","arxiv_id":"2411.18324","repositories_listed":3,"syntology":null},{"url":"/paper/diffusionner-boundary-diffusion-for-named","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","date":"2023-05-22","arxiv_id":"2305.13298","repositories_listed":3,"syntology":null},{"url":"/paper/finer-financial-named-entity-recognition","title":"FiNER-ORD: Financial Named Entity Recognition Open Research Dataset","date":"2023-02-22","arxiv_id":"2302.11157","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/xlm-v-overcoming-the-vocabulary-bottleneck-in","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models","date":"2023-01-25","arxiv_id":"2301.10472","repositories_listed":3,"syntology":null},{"url":"/paper/atco2-corpus-a-large-scale-dataset-for","title":"ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications","date":"2022-11-08","arxiv_id":"2211.04054","repositories_listed":3,"syntology":null},{"url":"/paper/an-analysis-of-simple-data-augmentation-for","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","date":"2020-10-22","arxiv_id":"2010.11683","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/bertweet-a-pre-trained-language-model-for","title":"BERTweet: A pre-trained language model for English Tweets","date":"2020-05-20","arxiv_id":"2005.10200","repositories_listed":3,"syntology":null},{"url":"/paper/mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","arxiv_id":"2005.00052","repositories_listed":3,"syntology":null},{"url":"/paper/beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","repositories_listed":3,"syntology":null},{"url":"/paper/parallel-sequence-tagging-for-concept","title":"Parallel sequence tagging for concept recognition","date":"2020-03-16","arxiv_id":"2003.07424","repositories_listed":3,"syntology":null},{"url":"/paper/cluener2020-fine-grained-name-entity","title":"CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese","date":"2020-01-13","arxiv_id":"2001.04351","repositories_listed":3,"syntology":null},{"url":"/paper/nested-named-entity-recognition-via-second","title":"Nested Named Entity Recognition via Second-best Sequence Learning and Decoding","date":"2019-09-05","arxiv_id":"1909.02250","repositories_listed":3,"syntology":null},{"url":"/paper/advancing-nlp-with-cognitive-language","title":"Advancing NLP with Cognitive Language Processing Signals","date":"2019-04-04","arxiv_id":"1904.02682","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/linspector-multilingual-probing-tasks-for","title":"LINSPECTOR: Multilingual Probing Tasks for Word Representations","date":"2019-03-22","arxiv_id":"1903.09442","repositories_listed":3,"syntology":null},{"url":"/paper/empower-sequence-labeling-with-task-aware","title":"Empower Sequence Labeling with Task-Aware Neural Language Model","date":"2017-09-13","arxiv_id":"1709.04109","repositories_listed":3,"syntology":null},{"url":"/paper/multimodal-llms-for-ocr-ocr-post-correction","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents","date":"2025-04-01","arxiv_id":"2504.00414","repositories_listed":2,"syntology":null},{"url":"/paper/whisperner-unified-open-named-entity-and","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","date":"2024-09-12","arxiv_id":"2409.08107","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-grounded-multimodal-named-entity","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","date":"2024-06-11","arxiv_id":"2406.07268","repositories_listed":2,"syntology":null},{"url":"/paper/do-english-named-entity-recognizers-work-well","title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?","date":"2024-04-20","arxiv_id":"2404.13465","repositories_listed":2,"syntology":null},{"url":"/paper/embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-negative-instances-for-generative","title":"Rethinking Negative Instances for Generative Named Entity Recognition","date":"2024-02-26","arxiv_id":"2402.16602","repositories_listed":2,"syntology":null},{"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/def2vec-extensible-word-embeddings-from","title":"Def2Vec: Extensible Word Embeddings from Dictionary Definitions","date":"2023-12-16","arxiv_id":null,"repositories_listed":2,"syntology":null}],"syntology_records":6,"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":"2026-09-25T09:33:49+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"}}