{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/wnut-2017-emerging-and-rare-entity","name":"WNUT 2017","full_name":"WNUT 2017 Emerging and Rare entity recognition","description_markdown":"This shared task focuses on identifying unusual, previously-unseen entities in the context of emerging discussions. Named entities form the basis of many modern approaches to other tasks (like event clustering and summarisation), but recall on them is a real problem in noisy text - even among annotators. This drop tends to be due to novel entities and surface forms. Take for example the tweet “so.. kktny in 30 mins?” - even human experts find entity kktny hard to detect and resolve. This task will evaluate the ability to detect and classify novel, emerging, singleton named entities in noisy text.\r\n\r\nThe goal of this task is to provide a definition of emerging and of rare entities, and based on that, also datasets for detecting these entities.","description_withheld":null,"homepage":"https://noisy-text.github.io/2017/emerging-rare-entities.html","introduced_date":"2017-09-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/results-of-the-wnut2017-shared-task-on-novel","title":"Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition","first_author":"Leon Derczynski","url":null},"license":{"name":"CC-BY 4.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"UIE","url":"/task/uie","datasets_with_task":"/datasets/task/uie"},{"name":"Few-shot NER","url":"/task/few-shot-ner","datasets_with_task":"/datasets/task/few-shot-ner"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Long-tail emerging entities","WNUT 2017","wnut_17"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/leondz/wnut_17","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Jnanesh12/Slang","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Kriyans/ner","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Kriyans/indian_names","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wnut_17","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":127,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-wnut-2017","task":"Named Entity Recognition (NER)","dataset_variant":"WNUT 2017","rows":23,"metrics":["F1","F1 (surface form)","Precision","Recall"],"first_row_in_archive_order":{"model":"CL-KL","paper":"/paper/improving-named-entity-recognition-by","metrics":{"F1":"60.45"},"code_links":[{"title":"modelscope/adaseq","url":"https://github.com/modelscope/adaseq"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/RaNER"},{"title":"Alibaba-NLP/CLNER","url":"https://github.com/Alibaba-NLP/CLNER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/uie-on-wnut-2017","task":"UIE","dataset_variant":"WNUT 2017","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"KnowCoder-7b-IE","paper":"/paper/knowcoder-coding-structured-knowledge-into","metrics":{"F1 score":"66.4"},"code_links":[{"title":"ICT-GoKnow/KnowCoder","url":"https://github.com/ICT-GoKnow/KnowCoder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":21,"of":21,"counts":{"papers_with_a_benchmark_row":21,"with_a_code_link":17,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":21,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/subregweigh-effective-and-efficient","slug":"subregweigh-effective-and-efficient","title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","date":"2024-09-10","arxiv_id":"2409.06216","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gollie-annotation-guidelines-improve-zero","slug":"gollie-annotation-guidelines-improve-zero","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","date":"2023-10-05","arxiv_id":"2310.03668","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":18,"samples_constructed":2,"samples_ran_checked":17,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["hitz-zentroa/gollie"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":2,"n_ran_no_instrument_failure":17,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gollie-annotation-guidelines-improve-zero#ran","syntology_url":"https://syntology.ai/paper/2310.03668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03668"}}}},{"paper":"/paper/a-global-context-mechanism-for-sequence","slug":"a-global-context-mechanism-for-sequence","title":"Supplementary Features of BiLSTM for Enhanced Sequence Labeling","date":"2023-05-31","arxiv_id":"2305.19928","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/t-ner-an-all-round-python-library-for-1","slug":"t-ner-an-all-round-python-library-for-1","title":"T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition","date":"2022-09-09","arxiv_id":"2209.12616","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["asahi417/tner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/t-ner-an-all-round-python-library-for-1#ran","syntology_url":"https://syntology.ai/paper/2209.12616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12616"}}}},{"paper":"/paper/adversarial-self-attention-for-language","slug":"adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","arxiv_id":"2206.12608","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hero-gang-neural-model-for-named-entity","slug":"hero-gang-neural-model-for-named-entity","title":"Hero-Gang Neural Model For Named Entity Recognition","date":"2022-05-15","arxiv_id":"2205.07177","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/miner-improving-out-of-vocabulary-named-1","slug":"miner-improving-out-of-vocabulary-named-1","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","date":"2022-04-09","arxiv_id":"2204.04391","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["beyonderxx/miner"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/miner-improving-out-of-vocabulary-named-1#ran","syntology_url":"https://syntology.ai/paper/2204.04391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.04391"}}}},{"paper":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}}}},{"paper":"/paper/inferner-an-attentive-model-leveraging-the","slug":"inferner-an-attentive-model-leveraging-the","title":"InferNER: an attentive model leveraging the sentence-level information for Named Entity Recognition in Microblogs","date":"2021-04-18","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/regularizing-models-via-pointwise-mutual","slug":"regularizing-models-via-pointwise-mutual","title":"Regularization for Long Named Entity Recognition","date":"2021-04-15","arxiv_id":"2104.07249","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improving-named-entity-recognition-with","slug":"improving-named-entity-recognition-with","title":"Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information","date":"2020-10-29","arxiv_id":"2010.15466","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/named-entity-recognition-for-social-media","slug":"named-entity-recognition-for-social-media","title":"Named Entity Recognition for Social Media Texts with Semantic Augmentation","date":"2020-10-29","arxiv_id":"2010.15458","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bertweet-a-pre-trained-language-model-for","slug":"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","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/robust-named-entity-recognition-with","slug":"robust-named-entity-recognition-with","title":"Robust Named Entity Recognition with Truecasing Pretraining","date":"2019-12-15","arxiv_id":"1912.07095","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/similarity-based-auxiliary-classifier-for","slug":"similarity-based-auxiliary-classifier-for","title":"Similarity Based Auxiliary Classifier for Named Entity Recognition","date":"2019-11-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/crossweigh-training-named-entity-tagger-from","slug":"crossweigh-training-named-entity-tagger-from","title":"CrossWeigh: Training Named Entity Tagger from Imperfect Annotations","date":"2019-09-03","arxiv_id":"1909.01441","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ZihanWangKi/CrossWeigh"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/crossweigh-training-named-entity-tagger-from#ran","syntology_url":"https://syntology.ai/paper/1909.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01441"}}}},{"paper":"/paper/remedying-bilstm-cnn-deficiency-in-modeling","slug":"remedying-bilstm-cnn-deficiency-in-modeling","title":"Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER","date":"2019-08-29","arxiv_id":"1908.11046","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/a-multi-task-approach-for-named-entity-1","slug":"a-multi-task-approach-for-named-entity-1","title":"A Multi-task Approach for Named Entity Recognition in Social Media Data","date":"2019-06-10","arxiv_id":"1906.04135","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/modeling-noisiness-to-recognize-named-1","slug":"modeling-noisiness-to-recognize-named-1","title":"Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media","date":"2019-06-10","arxiv_id":"1906.04129","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-and-sentence-level-features","slug":"transfer-learning-and-sentence-level-features","title":"Transfer Learning and Sentence Level Features for Named Entity Recognition on Tweets","date":"2017-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/subregweigh-effective-and-efficient","slug":"subregweigh-effective-and-efficient","title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","date":"2024-09-10","arxiv_id":"2409.06216","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gollie-annotation-guidelines-improve-zero","slug":"gollie-annotation-guidelines-improve-zero","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","date":"2023-10-05","arxiv_id":"2310.03668","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":18,"samples_constructed":2,"samples_ran_checked":17,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["hitz-zentroa/gollie"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":2,"n_ran_no_instrument_failure":17,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gollie-annotation-guidelines-improve-zero#ran","syntology_url":"https://syntology.ai/paper/2310.03668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03668"}}}},{"paper":"/paper/a-global-context-mechanism-for-sequence","slug":"a-global-context-mechanism-for-sequence","title":"Supplementary Features of BiLSTM for Enhanced Sequence Labeling","date":"2023-05-31","arxiv_id":"2305.19928","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/t-ner-an-all-round-python-library-for-1","slug":"t-ner-an-all-round-python-library-for-1","title":"T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition","date":"2022-09-09","arxiv_id":"2209.12616","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["asahi417/tner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/t-ner-an-all-round-python-library-for-1#ran","syntology_url":"https://syntology.ai/paper/2209.12616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12616"}}}},{"paper":"/paper/adversarial-self-attention-for-language","slug":"adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","arxiv_id":"2206.12608","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hero-gang-neural-model-for-named-entity","slug":"hero-gang-neural-model-for-named-entity","title":"Hero-Gang Neural Model For Named Entity Recognition","date":"2022-05-15","arxiv_id":"2205.07177","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/miner-improving-out-of-vocabulary-named-1","slug":"miner-improving-out-of-vocabulary-named-1","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","date":"2022-04-09","arxiv_id":"2204.04391","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["beyonderxx/miner"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/miner-improving-out-of-vocabulary-named-1#ran","syntology_url":"https://syntology.ai/paper/2204.04391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.04391"}}}},{"paper":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}}}},{"paper":"/paper/inferner-an-attentive-model-leveraging-the","slug":"inferner-an-attentive-model-leveraging-the","title":"InferNER: an attentive model leveraging the sentence-level information for Named Entity Recognition in Microblogs","date":"2021-04-18","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/regularizing-models-via-pointwise-mutual","slug":"regularizing-models-via-pointwise-mutual","title":"Regularization for Long Named Entity Recognition","date":"2021-04-15","arxiv_id":"2104.07249","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improving-named-entity-recognition-with","slug":"improving-named-entity-recognition-with","title":"Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information","date":"2020-10-29","arxiv_id":"2010.15466","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/named-entity-recognition-for-social-media","slug":"named-entity-recognition-for-social-media","title":"Named Entity Recognition for Social Media Texts with Semantic Augmentation","date":"2020-10-29","arxiv_id":"2010.15458","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bertweet-a-pre-trained-language-model-for","slug":"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","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/robust-named-entity-recognition-with","slug":"robust-named-entity-recognition-with","title":"Robust Named Entity Recognition with Truecasing Pretraining","date":"2019-12-15","arxiv_id":"1912.07095","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/similarity-based-auxiliary-classifier-for","slug":"similarity-based-auxiliary-classifier-for","title":"Similarity Based Auxiliary Classifier for Named Entity Recognition","date":"2019-11-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/crossweigh-training-named-entity-tagger-from","slug":"crossweigh-training-named-entity-tagger-from","title":"CrossWeigh: Training Named Entity Tagger from Imperfect Annotations","date":"2019-09-03","arxiv_id":"1909.01441","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ZihanWangKi/CrossWeigh"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/crossweigh-training-named-entity-tagger-from#ran","syntology_url":"https://syntology.ai/paper/1909.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01441"}}}},{"paper":"/paper/remedying-bilstm-cnn-deficiency-in-modeling","slug":"remedying-bilstm-cnn-deficiency-in-modeling","title":"Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER","date":"2019-08-29","arxiv_id":"1908.11046","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/a-multi-task-approach-for-named-entity-1","slug":"a-multi-task-approach-for-named-entity-1","title":"A Multi-task Approach for Named Entity Recognition in Social Media Data","date":"2019-06-10","arxiv_id":"1906.04135","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/modeling-noisiness-to-recognize-named-1","slug":"modeling-noisiness-to-recognize-named-1","title":"Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media","date":"2019-06-10","arxiv_id":"1906.04129","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-and-sentence-level-features","slug":"transfer-learning-and-sentence-level-features","title":"Transfer Learning and Sentence Level Features for Named Entity Recognition on Tweets","date":"2017-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/wnut-2017-emerging-and-rare-entity/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/wnut-2017-emerging-and-rare-entity/papers/ran/1","json":"/dataset/wnut-2017-emerging-and-rare-entity/papers/ran/1.json","rows":5}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":5,"samples_harvested":38,"samples_ran":30,"samples_constructed":2,"samples_ran_checked":24,"samples_ran_instrument_failed":6,"samples_unverified":8,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":5,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"be2a7669fe3a627c4d19d14dd8719a1646b5b9781d556befa97197da83211fcb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}