{"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":"/task/named-entity-recognition-ner/papers/7","list_of":"/task/named-entity-recognition-ner","task":"Named Entity Recognition (NER)","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_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'","n_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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":29,"rows_per_page":100,"rows":[601,700],"of":2874,"counts":{"archive_papers_tagged":2874,"with_a_code_link":955,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":2874,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":20,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/named-entity-recognition-ner","prev":"/task/named-entity-recognition-ner/papers/6","next":"/task/named-entity-recognition-ner/papers/8","papers":[{"url":"/paper/named-entity-recognition-with-small-strongly","slug":"named-entity-recognition-with-small-strongly","title":"Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data","date":"2021-06-16","arxiv_id":"2106.08977","repositories_listed":1,"syntology":null},{"url":"/paper/specializing-multilingual-language-models-an","slug":"specializing-multilingual-language-models-an","title":"Specializing Multilingual Language Models: An Empirical Study","date":"2021-06-16","arxiv_id":"2106.09063","repositories_listed":1,"syntology":null},{"url":"/paper/question-answering-infused-pre-training-of","slug":"question-answering-infused-pre-training-of","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","date":"2021-06-15","arxiv_id":"2106.08190","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/question-answering-infused-pre-training-of#ran","syntology_url":"https://syntology.ai/paper/2106.08190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08190"}},"official":{"repos":["facebookresearch/quip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cogalign-learning-to-align-textual-neural","slug":"cogalign-learning-to-align-textual-neural","title":"CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals","date":"2021-06-10","arxiv_id":"2106.05544","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/cogalign-learning-to-align-textual-neural#ran","syntology_url":"https://syntology.ai/paper/2106.05544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05544"}},"official":{"repos":["tjunlp-lab/CogAlign"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/advpicker-effectively-leveraging-unlabeled","slug":"advpicker-effectively-leveraging-unlabeled","title":"AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER","date":"2021-06-04","arxiv_id":"2106.02300","repositories_listed":1,"syntology":null},{"url":"/paper/syntax-augmented-multilingual-bert-for-cross","slug":"syntax-augmented-multilingual-bert-for-cross","title":"Syntax-augmented Multilingual BERT for Cross-lingual Transfer","date":"2021-06-03","arxiv_id":"2106.02134","repositories_listed":1,"syntology":null},{"url":"/paper/template-based-named-entity-recognition-using","slug":"template-based-named-entity-recognition-using","title":"Template-Based Named Entity Recognition Using BART","date":"2021-06-03","arxiv_id":"2106.01760","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-generative-framework-for-various","slug":"a-unified-generative-framework-for-various","title":"A Unified Generative Framework for Various NER Subtasks","date":"2021-06-02","arxiv_id":"2106.01223","repositories_listed":1,"syntology":null},{"url":"/paper/discontinuous-named-entity-recognition-as","slug":"discontinuous-named-entity-recognition-as","title":"Discontinuous Named Entity Recognition as Maximal Clique Discovery","date":"2021-06-01","arxiv_id":"2106.00218","repositories_listed":1,"syntology":null},{"url":"/paper/spanner-named-entity-re-recognition-as-span","slug":"spanner-named-entity-re-recognition-as-span","title":"SpanNER: Named Entity Re-/Recognition as Span Prediction","date":"2021-06-01","arxiv_id":"2106.00641","repositories_listed":1,"syntology":null},{"url":"/paper/the-biomaterials-annotator-a-system-for","slug":"the-biomaterials-annotator-a-system-for","title":"The Biomaterials Annotator: a system for ontology-based concept annotation of biomaterials text","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/crowdsourcing-learning-as-domain-adaptation-a","slug":"crowdsourcing-learning-as-domain-adaptation-a","title":"Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition","date":"2021-05-31","arxiv_id":"2105.14980","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crowdsourcing-learning-as-domain-adaptation-a#ran","syntology_url":"https://syntology.ai/paper/2105.14980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14980"}},"official":{"repos":["izhx/CLasDA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diakg-an-annotated-diabetes-dataset-for","slug":"diakg-an-annotated-diabetes-dataset-for","title":"DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction","date":"2021-05-31","arxiv_id":"2105.15033","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diakg-an-annotated-diabetes-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2105.15033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15033"}},"official":{"repos":["changdejie/diaKG-code"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cisco-at-semeval-2021-task-5-what-s-toxic","slug":"cisco-at-semeval-2021-task-5-what-s-toxic","title":"Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments","date":"2021-05-28","arxiv_id":"2105.13959","repositories_listed":1,"syntology":null},{"url":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scifive-a-text-to-text-transformer-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.03598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03598"}},"official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/weighted-training-for-cross-task-learning","slug":"weighted-training-for-cross-task-learning","title":"Weighted Training for Cross-Task Learning","date":"2021-05-28","arxiv_id":"2105.14095","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/weighted-training-for-cross-task-learning#ran","syntology_url":"https://syntology.ai/paper/2105.14095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14095"}},"official":{"repos":["HornHehhf/TAWT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dan-danish-nested-named-entities-and-lexical","slug":"dan-danish-nested-named-entities-and-lexical","title":"DaN+: Danish Nested Named Entities and Lexical Normalization","date":"2021-05-24","arxiv_id":"2105.11301","repositories_listed":1,"syntology":null},{"url":"/paper/a-sequence-to-set-network-for-nested-named","slug":"a-sequence-to-set-network-for-nested-named","title":"A Sequence-to-Set Network for Nested Named Entity Recognition","date":"2021-05-19","arxiv_id":"2105.08901","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-sequence-to-set-network-for-nested-named#ran","syntology_url":"https://syntology.ai/paper/2105.08901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08901"}},"official":{"repos":["zqtan1024/sequence-to-set"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-boundaries-end-to-end-recognition","slug":"rethinking-boundaries-end-to-end-recognition","title":"Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks","date":"2021-05-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lexicon-enhanced-chinese-sequence-labelling","slug":"lexicon-enhanced-chinese-sequence-labelling","title":"Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter","date":"2021-05-15","arxiv_id":"2105.07148","repositories_listed":1,"syntology":null},{"url":"/paper/locate-and-label-a-two-stage-identifier-for","slug":"locate-and-label-a-two-stage-identifier-for","title":"Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition","date":"2021-05-14","arxiv_id":"2105.06804","repositories_listed":1,"syntology":null},{"url":"/paper/switching-contexts-transportability-measures","slug":"switching-contexts-transportability-measures","title":"Switching Contexts: Transportability Measures for NLP","date":"2021-05-03","arxiv_id":"2105.00823","repositories_listed":1,"syntology":null},{"url":"/paper/t2ner-transformers-based-transfer-learning","slug":"t2ner-transformers-based-transfer-learning","title":"T2NER: Transformers based Transfer Learning Framework for Named Entity Recognition","date":"2021-04-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-biomedical-pretrained-language","slug":"improving-biomedical-pretrained-language","title":"Improving Biomedical Pretrained Language Models with Knowledge","date":"2021-04-21","arxiv_id":"2104.10344","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-temporal-drift-a-simple-approach","slug":"mitigating-temporal-drift-a-simple-approach","title":"Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp","date":"2021-04-20","arxiv_id":"2104.09742","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-noisy-labels-for-entity-centric","slug":"learning-from-noisy-labels-for-entity-centric","title":"Learning from Noisy Labels for Entity-Centric Information Extraction","date":"2021-04-17","arxiv_id":"2104.08656","repositories_listed":1,"syntology":null},{"url":"/paper/bert-memorisation-and-pitfalls-in-low","slug":"bert-memorisation-and-pitfalls-in-low","title":"Memorisation versus Generalisation in Pre-trained Language Models","date":"2021-04-16","arxiv_id":"2105.00828","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bert-memorisation-and-pitfalls-in-low#ran","syntology_url":"https://syntology.ai/paper/2105.00828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.00828"}},"official":{"repos":["Michael-Tanzer/BERT-mem-lowres"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bert-based-transformers-lead-the-way-in","slug":"bert-based-transformers-lead-the-way-in","title":"BERT based Transformers lead the way in Extraction of Health Information from Social Media","date":"2021-04-15","arxiv_id":"2104.07367","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/glara-graph-based-labeling-rule-augmentation","slug":"glara-graph-based-labeling-rule-augmentation","title":"GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition","date":"2021-04-13","arxiv_id":"2104.06230","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glara-graph-based-labeling-rule-augmentation#ran","syntology_url":"https://syntology.ai/paper/2104.06230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06230"}},"official":{"repos":["zhaoxy92/GLaRA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/better-feature-integration-for-named-entity","slug":"better-feature-integration-for-named-entity","title":"Better Feature Integration for Named Entity Recognition","date":"2021-04-12","arxiv_id":"2104.05316","repositories_listed":1,"syntology":null},{"url":"/paper/utnlp-at-semeval-2021-task-5-a-comparative","slug":"utnlp-at-semeval-2021-task-5-a-comparative","title":"UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models","date":"2021-04-10","arxiv_id":"2104.04770","repositories_listed":1,"syntology":null},{"url":"/paper/noisy-labeled-ner-with-confidence-estimation","slug":"noisy-labeled-ner-with-confidence-estimation","title":"Noisy-Labeled NER with Confidence Estimation","date":"2021-04-09","arxiv_id":"2104.04318","repositories_listed":1,"syntology":null},{"url":"/paper/covid-19-named-entity-recognition-for","slug":"covid-19-named-entity-recognition-for","title":"COVID-19 Named Entity Recognition for Vietnamese","date":"2021-04-08","arxiv_id":"2104.03879","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-pre-trained-language-models-for","slug":"benchmarking-pre-trained-language-models-for","title":"Benchmarking Pre-trained Language Models for Multilingual NER: TraSpaS at the BSNLP2021 Shared Task","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fuzzybio-a-proposal-for-fuzzy-representation","slug":"fuzzybio-a-proposal-for-fuzzy-representation","title":"FuzzyBIO: A Proposal for Fuzzy Representation of Discontinuous Entities","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/using-a-frustratingly-easy-domain-and-tagset","slug":"using-a-frustratingly-easy-domain-and-tagset","title":"Using a Frustratingly Easy Domain and Tagset Adaptation for Creating Slavic Named Entity Recognition Systems","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/textflint-unified-multilingual-robustness","slug":"textflint-unified-multilingual-robustness","title":"TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing","date":"2021-03-21","arxiv_id":"2103.11441","repositories_listed":1,"syntology":null},{"url":"/paper/bbw-matching-csv-to-wikidata-via-meta-lookup","slug":"bbw-matching-csv-to-wikidata-via-meta-lookup","title":"bbw: Matching CSV to Wikidata via Meta-lookup","date":"2021-03-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/anea-distant-supervision-for-low-resource","slug":"anea-distant-supervision-for-low-resource","title":"ANEA: Distant Supervision for Low-Resource Named Entity Recognition","date":"2021-02-25","arxiv_id":"2102.13129","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/anea-distant-supervision-for-low-resource#ran","syntology_url":"https://syntology.ai/paper/2102.13129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13129"}},"official":{"repos":["uds-lsv/anea"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/analysis-of-contextual-and-non-contextual","slug":"analysis-of-contextual-and-non-contextual","title":"Analysis Of Contextual and Non-Contextual Word Embedding Models For Hindi NER With Web Application For Data Collection","date":"2021-02-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-end-to-end-model-for-entity-level-relation","slug":"an-end-to-end-model-for-entity-level-relation","title":"An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning","date":"2021-02-11","arxiv_id":"2102.05980","repositories_listed":1,"syntology":null},{"url":"/paper/rpbert-a-text-image-relation-propagation","slug":"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/memorization-vs-generalization-quantifying","slug":"memorization-vs-generalization-quantifying","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","date":"2021-02-03","arxiv_id":"2102.01818","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-for-effective-multi-task-and","slug":"meta-learning-for-effective-multi-task-and","title":"Meta-Learning for Effective Multi-task and Multilingual Modelling","date":"2021-01-25","arxiv_id":"2101.10368","repositories_listed":1,"syntology":null},{"url":"/paper/skillner-mining-and-mapping-soft-skills-from","slug":"skillner-mining-and-mapping-soft-skills-from","title":"SkillNER: Mining and Mapping Soft Skills from any Text","date":"2021-01-22","arxiv_id":"2101.11431","repositories_listed":1,"syntology":null},{"url":"/paper/single-versus-multiple-annotation-for-named","slug":"single-versus-multiple-annotation-for-named","title":"Single versus Multiple Annotation for Named Entity Recognition of Mutations","date":"2021-01-19","arxiv_id":"2101.07450","repositories_listed":1,"syntology":null},{"url":"/paper/ai-and-hpc-enabled-lead-generation-for-sars","slug":"ai-and-hpc-enabled-lead-generation-for-sars","title":"AI- and HPC-enabled Lead Generation for SARS-CoV-2: Models and Processes to Extract Druglike Molecules Contained in Natural Language Text","date":"2021-01-12","arxiv_id":"2101.04617","repositories_listed":1,"syntology":null},{"url":"/paper/trankit-a-light-weight-transformer-based","slug":"trankit-a-light-weight-transformer-based","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","date":"2021-01-09","arxiv_id":"2101.03289","repositories_listed":1,"syntology":null},{"url":"/paper/phonlp-a-joint-multi-task-learning-model-for","slug":"phonlp-a-joint-multi-task-learning-model-for","title":"PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing","date":"2021-01-05","arxiv_id":"2101.01476","repositories_listed":1,"syntology":null},{"url":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","repositories_listed":1,"syntology":null},{"url":"/paper/how-do-your-biomedical-named-entity-models","slug":"how-do-your-biomedical-named-entity-models","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","date":"2021-01-01","arxiv_id":"2101.00160","repositories_listed":1,"syntology":null},{"url":"/paper/araelectra-pre-training-text-discriminators","slug":"araelectra-pre-training-text-discriminators","title":"AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding","date":"2020-12-31","arxiv_id":"2012.15516","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-disentangled-framework-for","slug":"semi-supervised-disentangled-framework-for","title":"Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition","date":"2020-12-22","arxiv_id":"2012.11805","repositories_listed":1,"syntology":null},{"url":"/paper/domain-specific-bert-representation-for-named","slug":"domain-specific-bert-representation-for-named","title":"Domain specific BERT representation for Named Entity Recognition of lab protocol","date":"2020-12-21","arxiv_id":"2012.11145","repositories_listed":1,"syntology":null},{"url":"/paper/sensitive-data-detection-with-high-throughput","slug":"sensitive-data-detection-with-high-throughput","title":"Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions","date":"2020-12-17","arxiv_id":"2012.09597","repositories_listed":1,"syntology":null},{"url":"/paper/nested-named-entity-recognition-with","slug":"nested-named-entity-recognition-with","title":"Nested Named Entity Recognition with Partially-Observed TreeCRFs","date":"2020-12-15","arxiv_id":"2012.08478","repositories_listed":1,"syntology":null},{"url":"/paper/recipenlg-a-cooking-recipes-dataset-for-semi","slug":"recipenlg-a-cooking-recipes-dataset-for-semi","title":"RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation","date":"2020-12-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/empirical-analysis-of-unlabeled-entity-1","slug":"empirical-analysis-of-unlabeled-entity-1","title":"Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition","date":"2020-12-10","arxiv_id":"2012.05426","repositories_listed":1,"syntology":null},{"url":"/paper/improving-clinical-document-understanding-on","slug":"improving-clinical-document-understanding-on","title":"Improving Clinical Document Understanding on COVID-19 Research with Spark NLP","date":"2020-12-07","arxiv_id":"2012.04005","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-embeddings-for-arabic-english-code","slug":"contextual-embeddings-for-arabic-english-code","title":"Contextual Embeddings for Arabic-English Code-Switched Data","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-recognition-for-chinese","slug":"named-entity-recognition-for-chinese","title":"Named Entity Recognition for Chinese biomedical patents","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-weave-corpus-annotating-synthetic","slug":"the-weave-corpus-annotating-synthetic","title":"The WEAVE Corpus: Annotating Synthetic Chemical Procedures in Patents with Chemical Named Entities","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-standardized-dataset-on-indonesian","slug":"towards-a-standardized-dataset-on-indonesian","title":"Towards a Standardized Dataset on Indonesian Named Entity Recognition","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-boundary-regressing-model-for-nested-named","slug":"a-boundary-regressing-model-for-nested-named","title":"A Boundary Regression Model for Nested Named Entity Recognition","date":"2020-11-29","arxiv_id":"2011.14330","repositories_listed":1,"syntology":null},{"url":"/paper/improving-biomedical-named-entity-recognition","slug":"improving-biomedical-named-entity-recognition","title":"Improving Biomedical Named Entity Recognition with Syntactic Information","date":"2020-11-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/flert-document-level-features-for-named","slug":"flert-document-level-features-for-named","title":"FLERT: Document-Level Features for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06993","repositories_listed":1,"syntology":null},{"url":"/paper/biomedical-named-entity-recognition-at-scale","slug":"biomedical-named-entity-recognition-at-scale","title":"Biomedical Named Entity Recognition at Scale","date":"2020-11-12","arxiv_id":"2011.06315","repositories_listed":1,"syntology":null},{"url":"/paper/indicnlpsuite-monolingual-corpora-evaluation","slug":"indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bionerflair-biomedical-named-entity","slug":"bionerflair-biomedical-named-entity","title":"BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger","date":"2020-11-03","arxiv_id":"2011.01504","repositories_listed":1,"syntology":null},{"url":"/paper/alleviating-digitization-errors-in-named","slug":"alleviating-digitization-errors-in-named","title":"Alleviating Digitization Errors in Named Entity Recognition for Historical Documents","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-generator-a-weakly-supervised","slug":"counterfactual-generator-a-weakly-supervised","title":"Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/iitkgp-at-w-nut-2020-shared-task-1-domain","slug":"iitkgp-at-w-nut-2020-shared-task-1-domain","title":"IITKGP at W-NUT 2020 Shared Task-1: Domain specific BERT representation for Named Entity Recognition of lab protocol","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/iobes-library-for-span-level-processing","slug":"iobes-library-for-span-level-processing","title":"iobes: Library for Span Level Processing","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mgsohrab-at-wnut-2020-shared-task-1-neural","slug":"mgsohrab-at-wnut-2020-shared-task-1-neural","title":"mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach for Entity and Relation Recognition Over Wet Lab Protocols","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/optsla-an-optimization-based-approach-for","slug":"optsla-an-optimization-based-approach-for","title":"OptSLA: an Optimization-Based Approach for Sequential Label Aggregation","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/senser-learning-cross-building-sensor","slug":"senser-learning-cross-building-sensor","title":"SeNsER: Learning Cross-Building Sensor Metadata Tagger","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/training-for-gibbs-sampling-on-conditional","slug":"training-for-gibbs-sampling-on-conditional","title":"Training for Gibbs Sampling on Conditional Random Fields with Neural Scoring Factors","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/wnut-2020-shared-task-1-conditional-random","slug":"wnut-2020-shared-task-1-conditional-random","title":"WNUT 2020 Shared Task-1: Conditional Random Field(CRF) based Named Entity Recognition(NER) for Wet Lab Protocols","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/wnut-2020-task-1-overview-extracting-entities","slug":"wnut-2020-task-1-overview-extracting-entities","title":"WNUT-2020 Task 1 Overview: Extracting Entities and Relations from Wet Lab Protocols","date":"2020-10-27","arxiv_id":"2010.14576","repositories_listed":1,"syntology":null},{"url":"/paper/disease-normalization-with-graph-embeddings","slug":"disease-normalization-with-graph-embeddings","title":"Disease Normalization with Graph Embeddings","date":"2020-10-24","arxiv_id":"2010.12925","repositories_listed":1,"syntology":null},{"url":"/paper/a-caption-is-worth-a-thousand-images","slug":"a-caption-is-worth-a-thousand-images","title":"Can images help recognize entities? A study of the role of images for Multimodal NER","date":"2020-10-23","arxiv_id":"2010.12712","repositories_listed":1,"syntology":null},{"url":"/paper/german-s-next-language-model","slug":"german-s-next-language-model","title":"German's Next Language Model","date":"2020-10-21","arxiv_id":"2010.10906","repositories_listed":1,"syntology":null},{"url":"/paper/umlsbert-clinical-domain-knowledge","slug":"umlsbert-clinical-domain-knowledge","title":"UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus","date":"2020-10-20","arxiv_id":"2010.10391","repositories_listed":1,"syntology":null},{"url":"/paper/coarse-to-fine-pre-training-for-named-entity","slug":"coarse-to-fine-pre-training-for-named-entity","title":"Coarse-to-Fine Pre-training for Named Entity Recognition","date":"2020-10-16","arxiv_id":"2010.08210","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":13,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/coarse-to-fine-pre-training-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/2010.08210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08210"}},"official":{"repos":["strawberryx/CoFEE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":9,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/named-entity-recognition-and-relation","slug":"named-entity-recognition-and-relation","title":"Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representations","date":"2020-10-15","arxiv_id":"2010.07522","repositories_listed":1,"syntology":null},{"url":"/paper/biomegatron-larger-biomedical-domain-language","slug":"biomegatron-larger-biomedical-domain-language","title":"BioMegatron: Larger Biomedical Domain Language Model","date":"2020-10-12","arxiv_id":"2010.06060","repositories_listed":1,"syntology":null},{"url":"/paper/constrained-decoding-for-computationally","slug":"constrained-decoding-for-computationally","title":"Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers","date":"2020-10-09","arxiv_id":"2010.04362","repositories_listed":1,"syntology":null},{"url":"/paper/iobes-a-library-for-span-level-processing","slug":"iobes-a-library-for-span-level-processing","title":"iobes: A Library for Span-Level Processing","date":"2020-10-09","arxiv_id":"2010.04373","repositories_listed":1,"syntology":null},{"url":"/paper/simple-and-effective-few-shot-named-entity","slug":"simple-and-effective-few-shot-named-entity","title":"Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning","date":"2020-10-06","arxiv_id":"2010.02405","repositories_listed":1,"syntology":null},{"url":"/paper/effective-unsupervised-domain-adaptation-with","slug":"effective-unsupervised-domain-adaptation-with","title":"Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models","date":"2020-10-05","arxiv_id":"2010.01739","repositories_listed":1,"syntology":null},{"url":"/paper/seqmix-augmenting-active-sequence-labeling","slug":"seqmix-augmenting-active-sequence-labeling","title":"SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup","date":"2020-10-05","arxiv_id":"2010.02322","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/seqmix-augmenting-active-sequence-labeling#ran","syntology_url":"https://syntology.ai/paper/2010.02322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02322"}},"official":{"repos":["rz-zhang/SeqMix"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/local-additivity-based-data-augmentation-for","slug":"local-additivity-based-data-augmentation-for","title":"Local Additivity Based Data Augmentation for Semi-supervised NER","date":"2020-10-04","arxiv_id":"2010.01677","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/local-additivity-based-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2010.01677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01677"}},"official":{"repos":["GT-SALT/LADA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/an-empirical-investigation-towards-efficient","slug":"an-empirical-investigation-towards-efficient","title":"An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training","date":"2020-10-01","arxiv_id":"2010.00784","repositories_listed":1,"syntology":null},{"url":"/paper/improving-vietnamese-named-entity-recognition","slug":"improving-vietnamese-named-entity-recognition","title":"Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models","date":"2020-10-01","arxiv_id":"2010.00198","repositories_listed":1,"syntology":null},{"url":"/paper/n-ltp-a-open-source-neural-chinese-language","slug":"n-ltp-a-open-source-neural-chinese-language","title":"N-LTP: An Open-source Neural Language Technology Platform for Chinese","date":"2020-09-24","arxiv_id":"2009.11616","repositories_listed":1,"syntology":null},{"url":"/paper/fasthan-a-bert-based-joint-many-task-toolkit","slug":"fasthan-a-bert-based-joint-many-task-toolkit","title":"fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP","date":"2020-09-18","arxiv_id":"2009.08633","repositories_listed":1,"syntology":null},{"url":"/paper/biomedical-named-entity-recognition-using","slug":"biomedical-named-entity-recognition-using","title":"Biomedical named entity recognition using BERT in the machine reading comprehension framework","date":"2020-09-03","arxiv_id":"2009.01560","repositories_listed":1,"syntology":null}],"record_sha256":"0f4650d646d521b144a7ac2ca864649d5bec05b1013296b6a066a4ddc9858e19","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}