{"url":"/task/entity-typing","name":"Entity Typing","slug":"entity-typing","description_markdown":"**Entity Typing** is an important task in text analysis. Assigning types (e.g., person, location, organization) to mentions of entities in documents enables effective structured analysis of unstructured text corpora. The extracted type information can be used in a wide range of ways (e.g., serving as primitives for information extraction and knowledge base (KB) completion, and assisting question answering). Traditional Entity Typing systems focus on a small set of coarse types (typically fewer than 10). Recent studies work on a much larger set of fine-grained types which form a tree-structured hierarchy (e.g., actor as a subtype of artist, and artist is a subtype of person).\r\n\r\n\r\n<span class=\"description-source\">Source: [Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding ](https://arxiv.org/abs/1602.05307)</span>\r\n\r\n<span class=\"description-source\">Image Credit: [Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding ](https://arxiv.org/abs/1602.05307)</span>","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":170,"papers_with_code":92,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":12,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/entity-typing-on-open-entity-1","slug":"entity-typing-on-open-entity-1","dataset":"Open Entity","dataset_url":"/dataset/open-entity-1","rows_in_archive":13,"metrics":["F1"],"first_row_in_archive_order":{"model":"MLMET","paper_title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","paper_url":"/paper/luke-deep-contextualized-entity","paper_date":"2020-10-02","arxiv_id":"2010.01057","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/roformer"},{"title":"studio-ousia/luke","url":"https://github.com/studio-ousia/luke"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/luke"},{"title":"JiachengLi1995/UCTopic","url":"https://github.com/JiachengLi1995/UCTopic"},{"title":"shmulvad/zero-for-ner","url":"https://github.com/shmulvad/zero-for-ner"},{"title":"Beacontownfc/paddle_luke_stable","url":"https://github.com/Beacontownfc/paddle_luke_stable"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/luke"},{"title":"2023-MindSpore-1/ms-code-156","url":"https://github.com/2023-MindSpore-1/ms-code-156"}],"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/entity-typing-on-ontonotes-v5-english","slug":"entity-typing-on-ontonotes-v5-english","dataset":"Ontonotes v5 (English)","dataset_url":"/dataset/ontonotes-5-0","rows_in_archive":4,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"MLMET","paper_title":"Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model","paper_url":"/paper/ultra-fine-entity-typing-with-weak","paper_date":"2021-06-08","arxiv_id":"2106.04098","code_links":[{"title":"HKUST-KnowComp/MLMET","url":"https://github.com/HKUST-KnowComp/MLMET"}],"syntology":null}},{"leaderboard":"/sota/entity-typing-on-open-entity","slug":"entity-typing-on-open-entity","dataset":"Open Entity","dataset_url":"/dataset/open-entity-1","rows_in_archive":3,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"K-Adapter ( fac-adapter )","paper_title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","paper_url":"/paper/k-adapter-infusing-knowledge-into-pre-trained","paper_date":"2020-02-05","arxiv_id":"2002.01808","code_links":[{"title":"microsoft/K-Adapter","url":"https://github.com/microsoft/K-Adapter"},{"title":"stevekgyang/sccl","url":"https://github.com/stevekgyang/sccl"}],"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/entity-typing-on-aida-conll","slug":"entity-typing-on-aida-conll","dataset":"AIDA-CoNLL","dataset_url":"/dataset/conll-1","rows_in_archive":1,"metrics":["Micro-F1"],"first_row_in_archive_order":{"model":"ReFinED","paper_title":"ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking","paper_url":"/paper/refined-an-efficient-zero-shot-capable-1","paper_date":"2022-07-08","arxiv_id":"2207.04108","code_links":[{"title":"amazon-science/ReFinED","url":"https://github.com/amazon-science/ReFinED"},{"title":"amazon-research/ReFinED","url":"https://github.com/amazon-research/ReFinED"},{"title":"alexa/refined","url":"https://github.com/alexa/refined"}],"syntology":null}},{"leaderboard":"/sota/entity-typing-on-docred-ie","slug":"entity-typing-on-docred-ie","dataset":"DocRED-IE","dataset_url":"/dataset/docred-ie","rows_in_archive":1,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"REXEL","paper_title":"REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking","paper_url":"/paper/rexel-an-end-to-end-model-for-document-level","paper_date":"2024-04-19","arxiv_id":"2404.12788","code_links":[{"title":"amazon-science/e2e-docie","url":"https://github.com/amazon-science/e2e-docie"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/entity-typing-on-figer","slug":"entity-typing-on-figer","dataset":"FIGER","dataset_url":"/dataset/figer","rows_in_archive":1,"metrics":["Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"LITE","paper_title":"Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference","paper_url":"/paper/ultra-fine-entity-typing-with-indirect","paper_date":"2022-02-12","arxiv_id":"2202.06167","code_links":[{"title":"luka-group/lite","url":"https://github.com/luka-group/lite"}],"syntology":null}},{"leaderboard":"/sota/entity-typing-on-freebase-figer","slug":"entity-typing-on-freebase-figer","dataset":"Freebase FIGER","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy","BEP","Macro F1","Micro F1","P@1"],"first_row_in_archive_order":{"model":"TextEnt-full","paper_title":"Representation Learning of Entities and Documents from Knowledge Base Descriptions","paper_url":"/paper/representation-learning-of-entities-and","paper_date":"2018-06-08","arxiv_id":"1806.02960","code_links":[{"title":"wikipedia2vec/wikipedia2vec","url":"https://github.com/wikipedia2vec/wikipedia2vec"},{"title":"studio-ousia/textent","url":"https://github.com/studio-ousia/textent"}],"syntology":null}},{"leaderboard":"/sota/entity-typing-on-ontonotes","slug":"entity-typing-on-ontonotes","dataset":"OntoNotes","dataset_url":"/dataset/ontonotes-5-0","rows_in_archive":1,"metrics":["Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"LITE","paper_title":"Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference","paper_url":"/paper/ultra-fine-entity-typing-with-indirect","paper_date":"2022-02-12","arxiv_id":"2202.06167","code_links":[{"title":"luka-group/lite","url":"https://github.com/luka-group/lite"}],"syntology":null}}],"datasets":[{"url":"/dataset/ontonotes-5-0","name":"OntoNotes 5.0","full_name":"","num_papers_in_archive":254},{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/figer","name":"FIGER","full_name":"Fine-Grained Entity Recognition","num_papers_in_archive":96},{"url":"/dataset/few-nerd","name":"Few-NERD","full_name":"Few-NERD","num_papers_in_archive":77},{"url":"/dataset/aida-conll-yago","name":"AIDA CoNLL-YAGO","full_name":"","num_papers_in_archive":64},{"url":"/dataset/open-entity-1","name":"Open Entity","full_name":"","num_papers_in_archive":35},{"url":"/dataset/preco","name":"PreCo","full_name":"","num_papers_in_archive":20},{"url":"/dataset/gum","name":"GUM","full_name":"Georgetown University Multilayer corpus","num_papers_in_archive":13},{"url":"/dataset/figment","name":"Figment","full_name":"","num_papers_in_archive":8},{"url":"/dataset/wikisrs","name":"WikiSRS","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/docred-ie","name":"DocRED-IE","full_name":"","num_papers_in_archive":1},{"url":"/dataset/htdm","name":"HTDM","full_name":"Hypertention Disease Medication","num_papers_in_archive":1}],"subtasks":[{"url":"/task/entity-typing-on-dh-kgs","name":"Entity Typing on DH-KGs"}],"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":92,"tagged_in_all":170,"items":[{"url":"/paper/luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","repositories_listed":9,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/refined-an-efficient-zero-shot-capable-1","title":"ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking","date":"2022-07-08","arxiv_id":"2207.04108","repositories_listed":3,"syntology":null},{"url":"/paper/semantic-relation-classification-via-1","title":"Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing","date":"2019-01-23","arxiv_id":"1901.08163","repositories_listed":3,"syntology":null},{"url":"/paper/label-noise-reduction-in-entity-typing-by","title":"Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding","date":"2016-02-17","arxiv_id":"1602.05307","repositories_listed":3,"syntology":null},{"url":"/paper/pie-a-parameter-and-inference-efficient","title":"PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning","date":"2022-04-29","arxiv_id":"2204.13957","repositories_listed":2,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","arxiv_id":"2002.01808","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/learning-to-few-shot-learn-across-diverse","title":"Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks","date":"2019-11-10","arxiv_id":"1911.03863","repositories_listed":2,"syntology":null},{"url":"/paper/mtab-matching-tabular-data-to-knowledge-graph","title":"MTab: Matching Tabular Data to Knowledge Graph using Probability Models","date":"2019-10-01","arxiv_id":"1910.00246","repositories_listed":2,"syntology":null},{"url":"/paper/enteval-a-holistic-evaluation-benchmark-for","title":"EntEval: A Holistic Evaluation Benchmark for Entity Representations","date":"2019-08-31","arxiv_id":"1909.00137","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","arxiv_id":"1905.07129","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/hierarchical-losses-and-new-resources-for","title":"Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking","date":"2018-07-13","arxiv_id":"1807.05127","repositories_listed":2,"syntology":null},{"url":"/paper/representation-learning-of-entities-and","title":"Representation Learning of Entities and Documents from Knowledge Base Descriptions","date":"2018-06-08","arxiv_id":"1806.02960","repositories_listed":2,"syntology":null},{"url":"/paper/refining-wikidata-taxonomy-using-large","title":"Refining Wikidata Taxonomy using Large Language Models","date":"2024-09-06","arxiv_id":"2409.04056","repositories_listed":1,"syntology":null},{"url":"/paper/rexel-an-end-to-end-model-for-document-level","title":"REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking","date":"2024-04-19","arxiv_id":"2404.12788","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-integration-of-semantic-and-structural","title":"The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing","date":"2024-04-12","arxiv_id":"2404.08313","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/modelling-commonsense-commonalities-with","title":"Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings","date":"2024-03-25","arxiv_id":"2403.16984","repositories_listed":1,"syntology":null},{"url":"/paper/decomposed-meta-learning-for-few-shot","title":"Decomposed Meta-Learning for Few-Shot Sequence Labeling","date":"2024-03-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/seed-guided-fine-grained-entity-typing-in","title":"Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains","date":"2024-01-23","arxiv_id":"2401.13129","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/robust-few-shot-named-entity-recognition-with","title":"Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification","date":"2023-12-13","arxiv_id":"2312.07961","repositories_listed":1,"syntology":null},{"url":"/paper/from-ultra-fine-to-fine-fine-tuning-ultra","title":"From Ultra-Fine to Fine: Fine-tuning Ultra-Fine Entity Typing Models to Fine-grained","date":"2023-12-11","arxiv_id":"2312.06188","repositories_listed":1,"syntology":null},{"url":"/paper/calibrated-seq2seq-models-for-efficient-and","title":"Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing","date":"2023-11-01","arxiv_id":"2311.00835","repositories_listed":1,"syntology":null},{"url":"/paper/dense-retrieval-as-indirect-supervision-for","title":"Dense Retrieval as Indirect Supervision for Large-space Decision Making","date":"2023-10-28","arxiv_id":"2310.18619","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-correct-noisy-labels-for-fine","title":"Learning to Correct Noisy Labels for Fine-Grained Entity Typing via Co-Prediction Prompt Tuning","date":"2023-10-23","arxiv_id":"2310.14596","repositories_listed":1,"syntology":null},{"url":"/paper/geolm-empowering-language-models-for","title":"GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding","date":"2023-10-23","arxiv_id":"2310.14478","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":11}},{"url":"/paper/do-language-models-learn-about-legal-entity","title":"Do Language Models Learn about Legal Entity Types during Pretraining?","date":"2023-10-19","arxiv_id":"2310.13092","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-contrastive-learning-for-entity","title":"Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs","date":"2023-10-18","arxiv_id":"2310.12008","repositories_listed":1,"syntology":null},{"url":"/paper/seqgpt-an-out-of-the-box-large-language-model","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","date":"2023-08-21","arxiv_id":"2308.10529","repositories_listed":1,"syntology":null},{"url":"/paper/promptner-prompt-locating-and-typing-for","title":"PromptNER: Prompt Locating and Typing for Named Entity Recognition","date":"2023-05-26","arxiv_id":"2305.17104","repositories_listed":1,"syntology":null},{"url":"/paper/encore-pre-training-entity-encoders-using","title":"EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains","date":"2023-05-22","arxiv_id":"2305.12924","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-named-entity-recognition","title":"Dynamic Named Entity Recognition","date":"2023-02-16","arxiv_id":"2302.10314","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}