{"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/2","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":2,"pages_in_order":29,"rows_per_page":100,"rows":[101,200],"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","next":"/task/named-entity-recognition-ner/papers/3","papers":[{"url":"/paper/bertifying-the-hidden-markov-model-for-multi","slug":"bertifying-the-hidden-markov-model-for-multi","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","date":"2021-05-26","arxiv_id":"2105.12848","repositories_listed":2,"syntology":{"n":20,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/bertifying-the-hidden-markov-model-for-multi#ran","syntology_url":"https://syntology.ai/paper/2105.12848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12848"}},"official":{"repos":["Yinghao-Li/CHMM-ALT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/optimizing-small-berts-trained-for-german-ner","slug":"optimizing-small-berts-trained-for-german-ner","title":"Optimizing small BERTs trained for German NER","date":"2021-04-23","arxiv_id":"2104.11559","repositories_listed":2,"syntology":null},{"url":"/paper/earnings-21-a-practical-benchmark-for-asr-in","slug":"earnings-21-a-practical-benchmark-for-asr-in","title":"Earnings-21: A Practical Benchmark for ASR in the Wild","date":"2021-04-22","arxiv_id":"2104.11348","repositories_listed":2,"syntology":null},{"url":"/paper/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","repositories_listed":2,"syntology":null},{"url":"/paper/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","repositories_listed":2,"syntology":null},{"url":"/paper/metaxl-meta-representation-transformation-for","slug":"metaxl-meta-representation-transformation-for","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","date":"2021-04-16","arxiv_id":"2104.07908","repositories_listed":2,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/metaxl-meta-representation-transformation-for#ran","syntology_url":"https://syntology.ai/paper/2104.07908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07908"}},"official":{"repos":["microsoft/MetaXL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/alephbert-a-hebrew-large-pre-trained-language","slug":"alephbert-a-hebrew-large-pre-trained-language","title":"AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With","date":"2021-04-08","arxiv_id":"2104.04052","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alephbert-a-hebrew-large-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2104.04052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04052"}},"official":{"repos":["OnlpLab/Hebrew-Sentiment-Data"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/masakhaner-named-entity-recognition-for","slug":"masakhaner-named-entity-recognition-for","title":"MasakhaNER: Named Entity Recognition for African Languages","date":"2021-03-22","arxiv_id":"2103.11811","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/masakhaner-named-entity-recognition-for#ran","syntology_url":"https://syntology.ai/paper/2103.11811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11811"}},"official":{"repos":["masakhane-io/masakhane-ner"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/structured-prediction-as-translation-between-1","slug":"structured-prediction-as-translation-between-1","title":"Structured Prediction as Translation between Augmented Natural Languages","date":"2021-01-14","arxiv_id":"2101.05779","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-named-entity-recognition-a","slug":"few-shot-named-entity-recognition-a","title":"Few-Shot Named Entity Recognition: A Comprehensive Study","date":"2020-12-29","arxiv_id":"2012.14978","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-deep-neural-networks-with","slug":"enhancing-deep-neural-networks-with","title":"Enhancing deep neural networks with morphological information","date":"2020-11-24","arxiv_id":"2011.12432","repositories_listed":2,"syntology":null},{"url":"/paper/interpretable-multi-dataset-evaluation-for","slug":"interpretable-multi-dataset-evaluation-for","title":"Interpretable Multi-dataset Evaluation for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06854","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-multi-dataset-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2011.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06854"}},"official":{"repos":["neulab/InterpretEval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/identifying-incorrect-labels-in-the-conll","slug":"identifying-incorrect-labels-in-the-conll","title":"Identifying Incorrect Labels in the CoNLL-2003 Corpus","date":"2020-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/a-frustratingly-easy-approach-for-joint","slug":"a-frustratingly-easy-approach-for-joint","title":"A Frustratingly Easy Approach for Entity and Relation Extraction","date":"2020-10-24","arxiv_id":"2010.12812","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-frustratingly-easy-approach-for-joint#ran","syntology_url":"https://syntology.ai/paper/2010.12812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12812"}},"official":{"repos":["princeton-nlp/PURE"],"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"]}}},{"url":"/paper/automated-concatenation-of-embeddings-for-1","slug":"automated-concatenation-of-embeddings-for-1","title":"Automated Concatenation of Embeddings for Structured Prediction","date":"2020-10-10","arxiv_id":"2010.05006","repositories_listed":2,"syntology":null},{"url":"/paper/two-are-better-than-one-joint-entity-and","slug":"two-are-better-than-one-joint-entity-and","title":"Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders","date":"2020-10-08","arxiv_id":"2010.03851","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/two-are-better-than-one-joint-entity-and#ran","syntology_url":"https://syntology.ai/paper/2010.03851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03851"}},"official":{"repos":["LorrinWWW/two-are-better-than-one"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/dwie-an-entity-centric-dataset-for-multi-task","slug":"dwie-an-entity-centric-dataset-for-multi-task","title":"DWIE: an entity-centric dataset for multi-task document-level information extraction","date":"2020-09-26","arxiv_id":"2009.12626","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dwie-an-entity-centric-dataset-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2009.12626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12626"}},"official":{"repos":["klimzaporojets/DWIE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hunflair-an-easy-to-use-tool-for-state-of-the","slug":"hunflair-an-easy-to-use-tool-for-state-of-the","title":"HunFlair: An Easy-to-Use Tool for State-of-the-Art Biomedical Named Entity Recognition","date":"2020-08-17","arxiv_id":"2008.07347","repositories_listed":2,"syntology":null},{"url":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","repositories_listed":2,"syntology":null},{"url":"/paper/advances-of-transformer-based-models-for-news","slug":"advances-of-transformer-based-models-for-news","title":"Advances of Transformer-Based Models for News Headline Generation","date":"2020-07-09","arxiv_id":"2007.05044","repositories_listed":2,"syntology":null},{"url":"/paper/pyramid-a-layered-model-for-nested-named","slug":"pyramid-a-layered-model-for-nested-named","title":"Pyramid: A Layered Model for Nested Named Entity Recognition","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/improving-sequence-tagging-for-vietnamese","slug":"improving-sequence-tagging-for-vietnamese","title":"Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models","date":"2020-06-29","arxiv_id":"2006.15994","repositories_listed":2,"syntology":null},{"url":"/paper/information-extraction-of-clinical-trial","slug":"information-extraction-of-clinical-trial","title":"Information Extraction of Clinical Trial Eligibility Criteria","date":"2020-06-12","arxiv_id":"2006.07296","repositories_listed":2,"syntology":null},{"url":"/paper/foreshadowing-the-benefits-of-incidental","slug":"foreshadowing-the-benefits-of-incidental","title":"Foreseeing the Benefits of Incidental Supervision","date":"2020-06-09","arxiv_id":"2006.05500","repositories_listed":2,"syntology":null},{"url":"/paper/code-and-named-entity-recognition-in","slug":"code-and-named-entity-recognition-in","title":"Code and Named Entity Recognition in StackOverflow","date":"2020-05-04","arxiv_id":"2005.01634","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/code-and-named-entity-recognition-in#ran","syntology_url":"https://syntology.ai/paper/2005.01634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.01634"}},"official":{"repos":["jeniyat/StackOverflowNER"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/word2vec-optimal-hyper-parameters-and-their","slug":"word2vec-optimal-hyper-parameters-and-their","title":"Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks","date":"2020-03-23","arxiv_id":"2003.11645","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/word2vec-optimal-hyper-parameters-and-their#ran","syntology_url":"https://syntology.ai/paper/2003.11645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11645"}},"official":{"repos":["tosingithub/sdesk"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/med7-a-transferable-clinical-natural-language","slug":"med7-a-transferable-clinical-natural-language","title":"Med7: a transferable clinical natural language processing model for electronic health records","date":"2020-03-03","arxiv_id":"2003.01271","repositories_listed":2,"syntology":null},{"url":"/paper/treynet-a-neural-model-for-text-localization","slug":"treynet-a-neural-model-for-text-localization","title":"A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages","date":"2019-12-20","arxiv_id":"1912.10016","repositories_listed":2,"syntology":null},{"url":"/paper/bertje-a-dutch-bert-model","slug":"bertje-a-dutch-bert-model","title":"BERTje: A Dutch BERT Model","date":"2019-12-19","arxiv_id":"1912.09582","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bertje-a-dutch-bert-model#ran","syntology_url":"https://syntology.ai/paper/1912.09582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.09582"}},"official":{"repos":["wietsedv/bertje"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mtab-matching-tabular-data-to-knowledge-graph","slug":"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/introducing-ronec-the-romanian-named-entity","slug":"introducing-ronec-the-romanian-named-entity","title":"Introducing RONEC -- the Romanian Named Entity Corpus","date":"2019-09-03","arxiv_id":"1909.01247","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchically-refined-label-attention","slug":"hierarchically-refined-label-attention","title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","date":"2019-08-23","arxiv_id":"1908.08676","repositories_listed":2,"syntology":null},{"url":"/paper/simplify-the-usage-of-lexicon-in-chinese-ner","slug":"simplify-the-usage-of-lexicon-in-chinese-ner","title":"Simplify the Usage of Lexicon in Chinese NER","date":"2019-08-16","arxiv_id":"1908.05969","repositories_listed":2,"syntology":null},{"url":"/paper/a-finnish-news-corpus-for-named-entity","slug":"a-finnish-news-corpus-for-named-entity","title":"A Finnish News Corpus for Named Entity Recognition","date":"2019-08-12","arxiv_id":"1908.04212","repositories_listed":2,"syntology":null},{"url":"/paper/delta-a-deep-learning-based-language","slug":"delta-a-deep-learning-based-language","title":"DELTA: A DEep learning based Language Technology plAtform","date":"2019-08-02","arxiv_id":"1908.01853","repositories_listed":2,"syntology":null},{"url":"/paper/robust-to-noise-models-in-natural-language","slug":"robust-to-noise-models-in-natural-language","title":"Robust to Noise Models in Natural Language Processing Tasks","date":"2019-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-named-entity-recognition-using-1","slug":"multilingual-named-entity-recognition-using-1","title":"Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF","date":"2019-06-21","arxiv_id":"1906.09978","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-with-whole-word-masking-for","slug":"pre-training-with-whole-word-masking-for","title":"Pre-Training with Whole Word Masking for Chinese BERT","date":"2019-06-19","arxiv_id":"1906.08101","repositories_listed":2,"syntology":null},{"url":"/paper/towards-robust-named-entity-recognition-for","slug":"towards-robust-named-entity-recognition-for","title":"Towards Robust Named Entity Recognition for Historic German","date":"2019-06-18","arxiv_id":"1906.07592","repositories_listed":2,"syntology":null},{"url":"/paper/practical-efficient-and-customizable-active","slug":"practical-efficient-and-customizable-active","title":"Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities","date":"2019-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/etnlp-a-toolkit-for-extraction-evaluation-and","slug":"etnlp-a-toolkit-for-extraction-evaluation-and","title":"ETNLP: a visual-aided systematic approach to select pre-trained embeddings for a downstream task","date":"2019-03-11","arxiv_id":"1903.04433","repositories_listed":2,"syntology":null},{"url":"/paper/star-transformer","slug":"star-transformer","title":"Star-Transformer","date":"2019-02-25","arxiv_id":"1902.09113","repositories_listed":2,"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/star-transformer#ran","syntology_url":"https://syntology.ai/paper/1902.09113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09113"}},"official":{"repos":["dmlc/dgl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/pioner-datasets-and-baselines-for-armenian","slug":"pioner-datasets-and-baselines-for-armenian","title":"pioNER: Datasets and Baselines for Armenian Named Entity Recognition","date":"2018-10-19","arxiv_id":"1810.08699","repositories_listed":2,"syntology":null},{"url":"/paper/semi-supervised-sequence-modeling-with-cross","slug":"semi-supervised-sequence-modeling-with-cross","title":"Semi-Supervised Sequence Modeling with Cross-View Training","date":"2018-09-22","arxiv_id":"1809.08370","repositories_listed":2,"syntology":null},{"url":"/paper/collabonet-collaboration-of-deep-neural","slug":"collabonet-collaboration-of-deep-neural","title":"CollaboNet: collaboration of deep neural networks for biomedical named entity recognition","date":"2018-09-21","arxiv_id":"1809.07950","repositories_listed":2,"syntology":null},{"url":"/paper/building-a-kannada-pos-tagger-using-machine","slug":"building-a-kannada-pos-tagger-using-machine","title":"Building a Kannada POS Tagger Using Machine Learning and Neural Network Models","date":"2018-08-09","arxiv_id":"1808.03175","repositories_listed":2,"syntology":null},{"url":"/paper/chinese-lexical-analysis-with-deep-bi-gru-crf","slug":"chinese-lexical-analysis-with-deep-bi-gru-crf","title":"Chinese Lexical Analysis with Deep Bi-GRU-CRF Network","date":"2018-07-05","arxiv_id":"1807.01882","repositories_listed":2,"syntology":null},{"url":"/paper/opentag-open-attribute-value-extraction-from","slug":"opentag-open-attribute-value-extraction-from","title":"OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]","date":"2018-06-01","arxiv_id":"1806.01264","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/opentag-open-attribute-value-extraction-from#ran","syntology_url":"https://syntology.ai/paper/1806.01264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01264"}},"official":null}},{"url":"/paper/baseline-needs-more-love-on-simple-word","slug":"baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","arxiv_id":"1805.09843","repositories_listed":2,"syntology":null},{"url":"/paper/sentence-state-lstm-for-text-representation","slug":"sentence-state-lstm-for-text-representation","title":"Sentence-State LSTM for Text Representation","date":"2018-05-07","arxiv_id":"1805.02474","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/sentence-state-lstm-for-text-representation#ran","syntology_url":"https://syntology.ai/paper/1805.02474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.02474"}},"official":null}},{"url":"/paper/a-deep-neural-network-model-for-the-task-of","slug":"a-deep-neural-network-model-for-the-task-of","title":"A Deep Neural Network Model for the Task of Named Entity Recognition","date":"2018-02-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/cross-type-biomedical-named-entity","slug":"cross-type-biomedical-named-entity","title":"Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning","date":"2018-01-30","arxiv_id":"1801.09851","repositories_listed":2,"syntology":null},{"url":"/paper/vncorenlp-a-vietnamese-natural-language","slug":"vncorenlp-a-vietnamese-natural-language","title":"VnCoreNLP: A Vietnamese Natural Language Processing Toolkit","date":"2018-01-04","arxiv_id":"1801.01331","repositories_listed":2,"syntology":null},{"url":"/paper/effective-use-of-bidirectional-language","slug":"effective-use-of-bidirectional-language","title":"Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition","date":"2017-11-21","arxiv_id":"1711.07908","repositories_listed":2,"syntology":null},{"url":"/paper/a-discourse-level-named-entity-recognition","slug":"a-discourse-level-named-entity-recognition","title":"A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text","date":"2017-11-19","arxiv_id":"1711.07010","repositories_listed":2,"syntology":null},{"url":"/paper/application-of-a-hybrid-bi-lstm-crf-model-to","slug":"application-of-a-hybrid-bi-lstm-crf-model-to","title":"Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition","date":"2017-09-27","arxiv_id":"1709.09686","repositories_listed":2,"syntology":null},{"url":"/paper/deep-active-learning-for-named-entity","slug":"deep-active-learning-for-named-entity","title":"Deep Active Learning for Named Entity Recognition","date":"2017-07-19","arxiv_id":"1707.05928","repositories_listed":2,"syntology":null},{"url":"/paper/context-dependent-sentiment-analysis-in-user","slug":"context-dependent-sentiment-analysis-in-user","title":"Context-Dependent Sentiment Analysis in User-Generated Videos","date":"2017-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pampo-using-pattern-matching-and-pos-tagging","slug":"pampo-using-pattern-matching-and-pos-tagging","title":"PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese","date":"2016-12-30","arxiv_id":"1612.09535","repositories_listed":2,"syntology":null},{"url":"/paper/towards-deep-learning-in-hindi-ner-an","slug":"towards-deep-learning-in-hindi-ner-an","title":"Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Scarcity","date":"2016-10-31","arxiv_id":"1610.09756","repositories_listed":2,"syntology":null},{"url":"/paper/harnessing-deep-neural-networks-with-logic","slug":"harnessing-deep-neural-networks-with-logic","title":"Harnessing Deep Neural Networks with Logic Rules","date":"2016-03-21","arxiv_id":"1603.06318","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-job-learning-with-bayesian-decision","slug":"on-the-job-learning-with-bayesian-decision","title":"On-the-Job Learning with Bayesian Decision Theory","date":"2015-06-10","arxiv_id":"1506.03140","repositories_listed":2,"syntology":null},{"url":"/paper/natural-language-processing-almost-from","slug":"natural-language-processing-almost-from","title":"Natural Language Processing (almost) from Scratch","date":"2011-03-02","arxiv_id":"1103.0398","repositories_listed":2,"syntology":null},{"url":"/paper/selecting-and-merging-towards-adaptable-and","slug":"selecting-and-merging-towards-adaptable-and","title":"Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models","date":"2025-06-28","arxiv_id":"2506.22813","repositories_listed":1,"syntology":null},{"url":"/paper/label-guided-in-context-learning-for-named","slug":"label-guided-in-context-learning-for-named","title":"Label-Guided In-Context Learning for Named Entity Recognition","date":"2025-05-29","arxiv_id":"2505.23722","repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-recognition-in-historical","slug":"named-entity-recognition-in-historical","title":"Named Entity Recognition in Historical Italian: The Case of Giacomo Leopardi's Zibaldone","date":"2025-05-26","arxiv_id":"2505.20113","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-analysis-of-static-word","slug":"a-comparative-analysis-of-static-word","title":"A Comparative Analysis of Static Word Embeddings for Hungarian","date":"2025-05-12","arxiv_id":"2505.07809","repositories_listed":1,"syntology":null},{"url":"/paper/methods-for-recognizing-nested-terms","slug":"methods-for-recognizing-nested-terms","title":"Methods for Recognizing Nested Terms","date":"2025-04-22","arxiv_id":"2504.16007","repositories_listed":1,"syntology":null},{"url":"/paper/myner-contextualized-burmese-named-entity","slug":"myner-contextualized-burmese-named-entity","title":"myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging","date":"2025-04-05","arxiv_id":"2504.04038","repositories_listed":1,"syntology":null},{"url":"/paper/gliner-biomed-a-suite-of-efficient-models-for","slug":"gliner-biomed-a-suite-of-efficient-models-for","title":"GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity Recognition","date":"2025-04-01","arxiv_id":"2504.00676","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-named-entity-recognition-2","slug":"transformer-based-named-entity-recognition-2","title":"Transformer-Based Named Entity Recognition for Automated Server Provisioning","date":"2025-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/student-powered-digital-scholarship-colab","slug":"student-powered-digital-scholarship-colab","title":"Student-Powered Digital Scholarship CoLab Project in the HKUST Library: Develop a Chinese Named-Entity Recognition (NER) Tool within One Semester from the Ground Up","date":"2025-03-29","arxiv_id":"2503.22967","repositories_listed":1,"syntology":null},{"url":"/paper/nercat-fine-tuning-for-enhanced-named-entity","slug":"nercat-fine-tuning-for-enhanced-named-entity","title":"NERCat: Fine-Tuning for Enhanced Named Entity Recognition in Catalan","date":"2025-03-18","arxiv_id":"2503.14173","repositories_listed":1,"syntology":null},{"url":"/paper/a-cooperative-multi-agent-framework-for-zero","slug":"a-cooperative-multi-agent-framework-for-zero","title":"A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition","date":"2025-02-25","arxiv_id":"2502.18702","repositories_listed":1,"syntology":null},{"url":"/paper/small-language-model-makes-an-effective-long","slug":"small-language-model-makes-an-effective-long","title":"Small Language Model Makes an Effective Long Text Extractor","date":"2025-02-11","arxiv_id":"2502.07286","repositories_listed":1,"syntology":null},{"url":"/paper/fewtopner-integrating-few-shot-learning-with","slug":"fewtopner-integrating-few-shot-learning-with","title":"FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework","date":"2025-02-04","arxiv_id":"2502.02391","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-projection-based-data-transfer-for","slug":"revisiting-projection-based-data-transfer-for","title":"Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages","date":"2025-01-30","arxiv_id":"2501.18750","repositories_listed":1,"syntology":null},{"url":"/paper/improving-dialectal-slot-and-intent-detection","slug":"improving-dialectal-slot-and-intent-detection","title":"Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study","date":"2025-01-07","arxiv_id":"2501.03863","repositories_listed":1,"syntology":null},{"url":"/paper/financial-named-entity-recognition-how-far","slug":"financial-named-entity-recognition-how-far","title":"Financial Named Entity Recognition: How Far Can LLM Go?","date":"2025-01-04","arxiv_id":"2501.02237","repositories_listed":1,"syntology":null},{"url":"/paper/the-role-of-natural-language-processing-tasks","slug":"the-role-of-natural-language-processing-tasks","title":"The Role of Natural Language Processing Tasks in Automatic Literary Character Network Construction","date":"2024-12-16","arxiv_id":"2412.11560","repositories_listed":1,"syntology":null},{"url":"/paper/familiarity-better-evaluation-of-zero-shot","slug":"familiarity-better-evaluation-of-zero-shot","title":"Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantifying Label Shifts in Synthetic Training Data","date":"2024-12-13","arxiv_id":"2412.10121","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-way-parallel-named-entity-annotated","slug":"a-multi-way-parallel-named-entity-annotated","title":"A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala","date":"2024-12-03","arxiv_id":"2412.02056","repositories_listed":1,"syntology":null},{"url":"/paper/baner-boundary-aware-llms-for-few-shot-named","slug":"baner-boundary-aware-llms-for-few-shot-named","title":"BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition","date":"2024-12-03","arxiv_id":"2412.02228","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-domain-adaptation-for-named-entity","slug":"few-shot-domain-adaptation-for-named-entity","title":"Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection","date":"2024-11-30","arxiv_id":"2412.00426","repositories_listed":1,"syntology":null},{"url":"/paper/information-extraction-from-clinical-notes","slug":"information-extraction-from-clinical-notes","title":"Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?","date":"2024-11-15","arxiv_id":"2411.10020","repositories_listed":1,"syntology":null},{"url":"/paper/link-synthesize-retrieve-universal-document","slug":"link-synthesize-retrieve-universal-document","title":"Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval","date":"2024-10-24","arxiv_id":"2410.18385","repositories_listed":1,"syntology":null},{"url":"/paper/skill-llm-repurposing-general-purpose-llms","slug":"skill-llm-repurposing-general-purpose-llms","title":"Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction","date":"2024-10-15","arxiv_id":"2410.12052","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-ocr-sensitive-neurons-to","slug":"investigating-ocr-sensitive-neurons-to","title":"Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical Documents","date":"2024-09-25","arxiv_id":"2409.16934","repositories_listed":1,"syntology":null},{"url":"/paper/effectiveness-of-cross-linguistic-extraction","slug":"effectiveness-of-cross-linguistic-extraction","title":"Effectiveness of Cross-linguistic Extraction of Genetic Information using Generative Large Language Models","date":"2024-09-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/slimer-it-zero-shot-ner-on-italian-language","slug":"slimer-it-zero-shot-ner-on-italian-language","title":"SLIMER-IT: Zero-Shot NER on Italian Language","date":"2024-09-24","arxiv_id":"2409.15933","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic4health-generating-annotated","slug":"synthetic4health-generating-annotated","title":"Synthetic4Health: Generating Annotated Synthetic Clinical Letters","date":"2024-09-14","arxiv_id":"2409.09501","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-named-entity-recognition-using-few","slug":"evaluating-named-entity-recognition-using-few","title":"Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language Models","date":"2024-08-28","arxiv_id":"2408.15796","repositories_listed":1,"syntology":null},{"url":"/paper/fsponer-few-shot-prompt-optimization-for","slug":"fsponer-few-shot-prompt-optimization-for","title":"FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios","date":"2024-07-10","arxiv_id":"2407.08035","repositories_listed":1,"syntology":null},{"url":"/paper/are-data-augmentation-methods-in-named-entity","slug":"are-data-augmentation-methods-in-named-entity","title":"Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?","date":"2024-07-02","arxiv_id":"2407.02062","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-multilingual-llms-to-low-resource","slug":"adapting-multilingual-llms-to-low-resource","title":"Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters","date":"2024-07-01","arxiv_id":"2407.01406","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-struggle-in-token-level","slug":"large-language-models-struggle-in-token-level","title":"Large Language Models Struggle in Token-Level Clinical Named Entity Recognition","date":"2024-06-30","arxiv_id":"2407.00731","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-instruction-tuning-for","slug":"retrieval-augmented-instruction-tuning-for","title":"Retrieval Augmented Instruction Tuning for Open NER with Large Language Models","date":"2024-06-25","arxiv_id":"2406.17305","repositories_listed":1,"syntology":null},{"url":"/paper/medical-spoken-named-entity-recognition","slug":"medical-spoken-named-entity-recognition","title":"Medical Spoken Named Entity Recognition","date":"2024-06-19","arxiv_id":"2406.13337","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-boundaries-learning-a-universal-entity","slug":"beyond-boundaries-learning-a-universal-entity","title":"Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition","date":"2024-06-17","arxiv_id":"2406.11192","repositories_listed":1,"syntology":null}],"record_sha256":"efb0e052762478e35719499fb2d84109d617798926772318163d7c4a69b11ca7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}