{"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/part-of-speech-tagging","name":"Part-Of-Speech Tagging","slug":"part-of-speech-tagging","description_markdown":"Part-of-speech tagging (POS tagging) is the task of tagging a word in a text with its part of speech.\r\nA part of speech is a category of words with similar grammatical properties. Common English\r\nparts of speech are noun, verb, adjective, adverb, pronoun, preposition, conjunction, etc.\r\n\r\nExample: \r\n\r\n| Vinken | , | 61 | years | old |\r\n| --- | ---| --- | --- | --- |\r\n| NNP | , | CD | NNS | JJ |","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":990,"papers_with_code":228,"benchmarks":15,"benchmark_tables_in_archive":15,"benchmark_tables_shown":15,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":26,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","slug":"part-of-speech-tagging-on-penn-treebank","dataset":"Penn Treebank","dataset_url":"/dataset/penn-treebank","rows_in_archive":20,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SALE-BART encoder","paper_title":"Sequence Alignment Ensemble with a Single Neural Network for Sequence Labeling","paper_url":"/paper/sequence-alignment-ensemble-with-a-single","paper_date":"2022-07-07","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-ud","slug":"part-of-speech-tagging-on-ud","dataset":"UD","dataset_url":"/dataset/universal-dependencies","rows_in_archive":5,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"BiLSTM-LAN","paper_title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","paper_url":"/paper/hierarchically-refined-label-attention","paper_date":"2019-08-23","arxiv_id":"1908.08676","code_links":[{"title":"Nealcly/LAN","url":"https://github.com/Nealcly/LAN"},{"title":"Nealcly/BiLSTM-LAN","url":"https://github.com/Nealcly/BiLSTM-LAN"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-ritter","slug":"part-of-speech-tagging-on-ritter","dataset":"Ritter","dataset_url":null,"rows_in_archive":4,"metrics":["Acc"],"first_row_in_archive_order":{"model":"ACE","paper_title":"Automated Concatenation of Embeddings for Structured Prediction","paper_url":"/paper/automated-concatenation-of-embeddings-for-1","paper_date":"2020-10-10","arxiv_id":"2010.05006","code_links":[{"title":"Alibaba-NLP/ACE","url":"https://github.com/Alibaba-NLP/ACE"},{"title":"zhaoyuesun/phee","url":"https://github.com/zhaoyuesun/phee"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-ark","slug":"part-of-speech-tagging-on-ark","dataset":"ARK","dataset_url":null,"rows_in_archive":3,"metrics":["Acc"],"first_row_in_archive_order":{"model":"ACE","paper_title":"Automated Concatenation of Embeddings for Structured Prediction","paper_url":"/paper/automated-concatenation-of-embeddings-for-1","paper_date":"2020-10-10","arxiv_id":"2010.05006","code_links":[{"title":"Alibaba-NLP/ACE","url":"https://github.com/Alibaba-NLP/ACE"},{"title":"zhaoyuesun/phee","url":"https://github.com/zhaoyuesun/phee"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-social-media","slug":"part-of-speech-tagging-on-social-media","dataset":"Social media","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PretRand","paper_title":"Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging","paper_url":"/paper/joint-learning-of-pre-trained-and-random","paper_date":"2019-04-07","arxiv_id":"1904.03595","code_links":[],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-tweebank","slug":"part-of-speech-tagging-on-tweebank","dataset":"Tweebank","dataset_url":"/dataset/tweebank","rows_in_archive":3,"metrics":["Acc"],"first_row_in_archive_order":{"model":"ACE","paper_title":"Automated Concatenation of Embeddings for Structured Prediction","paper_url":"/paper/automated-concatenation-of-embeddings-for-1","paper_date":"2020-10-10","arxiv_id":"2010.05006","code_links":[{"title":"Alibaba-NLP/ACE","url":"https://github.com/Alibaba-NLP/ACE"},{"title":"zhaoyuesun/phee","url":"https://github.com/zhaoyuesun/phee"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-ud2-5-test","slug":"part-of-speech-tagging-on-ud2-5-test","dataset":"UD2.5 test","dataset_url":null,"rows_in_archive":2,"metrics":["Macro-averaged F1"],"first_row_in_archive_order":{"model":"Trankit","paper_title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","paper_url":"/paper/trankit-a-light-weight-transformer-based","paper_date":"2021-01-09","arxiv_id":"2101.03289","code_links":[{"title":"nlp-uoregon/trankit","url":"https://github.com/nlp-uoregon/trankit"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-antilles","slug":"part-of-speech-tagging-on-antilles","dataset":"ANTILLES","dataset_url":"/dataset/antilles","rows_in_archive":1,"metrics":["Weighted Average F1-score"],"first_row_in_archive_order":{"model":"Bi-LSTM-CRF + Flair Embeddings + CamemBERT (oscar−138gb−base) Embeddings","paper_title":"ANTILLES: An Open French Linguistically Enriched Part-of-Speech Corpus","paper_url":"/paper/antilles-an-open-french-linguistically","paper_date":"2022-06-20","arxiv_id":null,"code_links":[{"title":"qanastek/ANTILLES","url":"https://github.com/qanastek/ANTILLES"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-dane","slug":"part-of-speech-tagging-on-dane","dataset":"DaNE","dataset_url":"/dataset/dane","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"da_dacy_large_tft-0.0.0","paper_title":"DaCy: A Unified Framework for Danish NLP","paper_url":"/paper/dacy-a-unified-framework-for-danish-nlp","paper_date":"2021-07-12","arxiv_id":"2107.05295","code_links":[],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-french-gsd","slug":"part-of-speech-tagging-on-french-gsd","dataset":"French GSD","dataset_url":null,"rows_in_archive":1,"metrics":["UPOS"],"first_row_in_archive_order":{"model":"CamemBERT","paper_title":"CamemBERT: a Tasty French Language Model","paper_url":"/paper/camembert-a-tasty-french-language-model","paper_date":"2019-11-10","arxiv_id":"1911.03894","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"anaishoareau/french_preprocessing","url":"https://github.com/anaishoareau/french_preprocessing"},{"title":"bourrel/French-News-Clustering","url":"https://github.com/bourrel/French-News-Clustering"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/camembert"},{"title":"hbaflast/bert-sentiment-analysis-pytorch","url":"https://github.com/hbaflast/bert-sentiment-analysis-pytorch"},{"title":"hbaflast/bert-sentiment-analysis-tensorflow","url":"https://github.com/hbaflast/bert-sentiment-analysis-tensorflow"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/camembert"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-morphosyntactic","slug":"part-of-speech-tagging-on-morphosyntactic","dataset":"Morphosyntactic-analysis-dataset","dataset_url":"/dataset/morphosyntactic-analysis-dataset","rows_in_archive":1,"metrics":["BLEX"],"first_row_in_archive_order":{"model":"MyBert","paper_title":"Towards Deep Learning Models Resistant to Adversarial Attacks","paper_url":"/paper/towards-deep-learning-models-resistant-to","paper_date":"2017-06-19","arxiv_id":"1706.06083","code_links":[{"title":"cleverhans-lab/cleverhans","url":"https://github.com/cleverhans-lab/cleverhans"},{"title":"openai/cleverhans","url":"https://github.com/openai/cleverhans"},{"title":"tensorflow/cleverhans","url":"https://github.com/tensorflow/cleverhans"},{"title":"MadryLab/mnist_challenge","url":"https://github.com/MadryLab/mnist_challenge"},{"title":"MadryLab/cifar10_challenge","url":"https://github.com/MadryLab/cifar10_challenge"},{"title":"locuslab/convex_adversarial","url":"https://github.com/locuslab/convex_adversarial"},{"title":"ndb796/pytorch-adversarial-training-cifar","url":"https://github.com/ndb796/pytorch-adversarial-training-cifar"},{"title":"locuslab/robust_overfitting","url":"https://github.com/locuslab/robust_overfitting"},{"title":"zjfheart/Friendly-Adversarial-Training","url":"https://github.com/zjfheart/Friendly-Adversarial-Training"},{"title":"imrahulr/adversarial_robustness_pytorch","url":"https://github.com/imrahulr/adversarial_robustness_pytorch"},{"title":"Jeffkang-94/pytorch-adversarial-attack","url":"https://github.com/Jeffkang-94/pytorch-adversarial-attack"},{"title":"P2333/Max-Mahalanobis-Training","url":"https://github.com/P2333/Max-Mahalanobis-Training"},{"title":"revbucket/mister_ed","url":"https://github.com/revbucket/mister_ed"},{"title":"Zoky-2020/Set-level_Guidance_Attack","url":"https://github.com/Zoky-2020/Set-level_Guidance_Attack"},{"title":"tianzheng4/Distributionally-Adversarial-Attack","url":"https://github.com/tianzheng4/Distributionally-Adversarial-Attack"},{"title":"arobey1/advbench","url":"https://github.com/arobey1/advbench"},{"title":"Hadisalman/robust-verify-benchmark","url":"https://github.com/Hadisalman/robust-verify-benchmark"},{"title":"zibojia/rslad","url":"https://github.com/zibojia/rslad"},{"title":"henry8527/GCE","url":"https://github.com/henry8527/GCE"},{"title":"albertmillan/adversarial-training-pytorch","url":"https://github.com/albertmillan/adversarial-training-pytorch"},{"title":"EPFL-VILAB/XDEnsembles","url":"https://github.com/EPFL-VILAB/XDEnsembles"},{"title":"andrewilyas/ens-adv-train-attack","url":"https://github.com/andrewilyas/ens-adv-train-attack"},{"title":"boyellow/adaad","url":"https://github.com/boyellow/adaad"},{"title":"cdluminate/advrank","url":"https://github.com/cdluminate/advrank"},{"title":"cdluminate/advrank-pub","url":"https://github.com/cdluminate/advrank-pub"},{"title":"AI-secure/Transferability-Reduced-Smooth-Ensemble","url":"https://github.com/AI-secure/Transferability-Reduced-Smooth-Ensemble"},{"title":"ucsb-nlp-chang/textgrad","url":"https://github.com/ucsb-nlp-chang/textgrad"},{"title":"luizgh/adversarial_signatures","url":"https://github.com/luizgh/adversarial_signatures"},{"title":"arobey1/mbrdl","url":"https://github.com/arobey1/mbrdl"},{"title":"microsoft/distance-learner","url":"https://github.com/microsoft/distance-learner"},{"title":"scenarri/s2m-tea","url":"https://github.com/scenarri/s2m-tea"},{"title":"VishaalMK/VectorDefense","url":"https://github.com/VishaalMK/VectorDefense"},{"title":"hrdwsong/TDLMR2AA-Paddle","url":"https://github.com/hrdwsong/TDLMR2AA-Paddle"},{"title":"val-iisc/flss","url":"https://github.com/val-iisc/flss"},{"title":"cs-giung/course-dl-TP","url":"https://github.com/cs-giung/course-dl-TP"},{"title":"eldadp100/cnn_course_final","url":"https://github.com/eldadp100/cnn_course_final"},{"title":"eldadp100/Towards-Deep-Learning-Models-Resistant-to-Adversarial-Attacks-Implementation","url":"https://github.com/eldadp100/Towards-Deep-Learning-Models-Resistant-to-Adversarial-Attacks-Implementation"},{"title":"bingcheng45/hnr-extension","url":"https://github.com/bingcheng45/hnr-extension"},{"title":"ee17b031-iittp/Projected-Gradient-Descent-with-CIFAR10","url":"https://github.com/ee17b031-iittp/Projected-Gradient-Descent-with-CIFAR10"},{"title":"salomonhotegni/MOREL","url":"https://github.com/salomonhotegni/MOREL"},{"title":"loes5307/vocaladversary2022","url":"https://github.com/loes5307/vocaladversary2022"},{"title":"KnowledgeDiscovery/FaceSec","url":"https://github.com/KnowledgeDiscovery/FaceSec"},{"title":"lemonadec/Relevance-between-Accuracy-under-Black-box-Attack-and-the-Similarity-between-Networks","url":"https://github.com/lemonadec/Relevance-between-Accuracy-under-Black-box-Attack-and-the-Similarity-between-Networks"},{"title":"amerch/CIFAR100-Training","url":"https://github.com/amerch/CIFAR100-Training"},{"title":"matanbt/attack-tabular","url":"https://github.com/matanbt/attack-tabular"},{"title":"bethgelab/cifar10_challenge","url":"https://github.com/bethgelab/cifar10_challenge"},{"title":"peck94/cann-detector","url":"https://github.com/peck94/cann-detector"},{"title":"abahram77/mnist_challenge","url":"https://github.com/abahram77/mnist_challenge"},{"title":"thomashopkins32/PGDAdversarialLearning","url":"https://github.com/thomashopkins32/PGDAdversarialLearning"},{"title":"jokeryan/post_training","url":"https://github.com/jokeryan/post_training"},{"title":"TonyYaoMSU/ProjectedGradientDescent","url":"https://github.com/TonyYaoMSU/ProjectedGradientDescent"},{"title":"dacostaHugo/Adversarial_attacks","url":"https://github.com/dacostaHugo/Adversarial_attacks"},{"title":"khieu/cifar10_challenge","url":"https://github.com/khieu/cifar10_challenge"},{"title":"SafiyaJan/Attacking-Neural-Networks","url":"https://github.com/SafiyaJan/Attacking-Neural-Networks"},{"title":"shashankskagnihotri/adv-corrected-ddcat-cospgd","url":"https://github.com/shashankskagnihotri/adv-corrected-ddcat-cospgd"},{"title":"hope-yao/robust_attention_cifar","url":"https://github.com/hope-yao/robust_attention_cifar"},{"title":"Cadden/paddle-adver","url":"https://github.com/Cadden/paddle-adver"},{"title":"YinDFY/PGD_for_targeted_attack","url":"https://github.com/YinDFY/PGD_for_targeted_attack"},{"title":"abahram77/mnistChallenge","url":"https://github.com/abahram77/mnistChallenge"}],"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"9 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; 7 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/towards-deep-learning-models-resistant-to#ran","syntology_url":"https://syntology.ai/paper/1706.06083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.06083"}},"official":{"repos":["MadryLab/cifar10_challenge","MadryLab/mnist_challenge"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/part-of-speech-tagging-on-partut","slug":"part-of-speech-tagging-on-partut","dataset":"ParTUT","dataset_url":null,"rows_in_archive":1,"metrics":["UPOS"],"first_row_in_archive_order":{"model":"CamemBERT","paper_title":"CamemBERT: a Tasty French Language Model","paper_url":"/paper/camembert-a-tasty-french-language-model","paper_date":"2019-11-10","arxiv_id":"1911.03894","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"anaishoareau/french_preprocessing","url":"https://github.com/anaishoareau/french_preprocessing"},{"title":"bourrel/French-News-Clustering","url":"https://github.com/bourrel/French-News-Clustering"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/camembert"},{"title":"hbaflast/bert-sentiment-analysis-pytorch","url":"https://github.com/hbaflast/bert-sentiment-analysis-pytorch"},{"title":"hbaflast/bert-sentiment-analysis-tensorflow","url":"https://github.com/hbaflast/bert-sentiment-analysis-tensorflow"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/camembert"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-sequoia-treebank","slug":"part-of-speech-tagging-on-sequoia-treebank","dataset":"Sequoia Treebank","dataset_url":null,"rows_in_archive":1,"metrics":["UPOS"],"first_row_in_archive_order":{"model":"CamemBERT","paper_title":"CamemBERT: a Tasty French Language Model","paper_url":"/paper/camembert-a-tasty-french-language-model","paper_date":"2019-11-10","arxiv_id":"1911.03894","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"anaishoareau/french_preprocessing","url":"https://github.com/anaishoareau/french_preprocessing"},{"title":"bourrel/French-News-Clustering","url":"https://github.com/bourrel/French-News-Clustering"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/camembert"},{"title":"hbaflast/bert-sentiment-analysis-pytorch","url":"https://github.com/hbaflast/bert-sentiment-analysis-pytorch"},{"title":"hbaflast/bert-sentiment-analysis-tensorflow","url":"https://github.com/hbaflast/bert-sentiment-analysis-tensorflow"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/camembert"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-spoken-corpus","slug":"part-of-speech-tagging-on-spoken-corpus","dataset":"Spoken Corpus","dataset_url":null,"rows_in_archive":1,"metrics":["UPOS"],"first_row_in_archive_order":{"model":"CamemBERT","paper_title":"CamemBERT: a Tasty French Language Model","paper_url":"/paper/camembert-a-tasty-french-language-model","paper_date":"2019-11-10","arxiv_id":"1911.03894","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"anaishoareau/french_preprocessing","url":"https://github.com/anaishoareau/french_preprocessing"},{"title":"bourrel/French-News-Clustering","url":"https://github.com/bourrel/French-News-Clustering"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/camembert"},{"title":"hbaflast/bert-sentiment-analysis-pytorch","url":"https://github.com/hbaflast/bert-sentiment-analysis-pytorch"},{"title":"hbaflast/bert-sentiment-analysis-tensorflow","url":"https://github.com/hbaflast/bert-sentiment-analysis-tensorflow"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/camembert"}],"syntology":null}},{"leaderboard":"/sota/part-of-speech-tagging-on-xglue","slug":"part-of-speech-tagging-on-xglue","dataset":"XGLUE","dataset_url":"/dataset/xglue","rows_in_archive":1,"metrics":["Avg. F1"],"first_row_in_archive_order":{"model":"mGPT","paper_title":"mGPT: Few-Shot Learners Go Multilingual","paper_url":"/paper/mgpt-few-shot-learners-go-multilingual","paper_date":"2022-04-15","arxiv_id":"2204.07580","code_links":[{"title":"ai-forever/mgpt","url":"https://github.com/ai-forever/mgpt"}],"syntology":null}}],"datasets":[{"url":"/dataset/penn-treebank","name":"Penn Treebank","full_name":"","num_papers_in_archive":1006},{"url":"/dataset/universal-dependencies","name":"Universal Dependencies","full_name":"","num_papers_in_archive":520},{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/conll-2002","name":"CoNLL 2002","full_name":"","num_papers_in_archive":70},{"url":"/dataset/english-web-treebank","name":"English Web Treebank","full_name":"English Web Treebank","num_papers_in_archive":42},{"url":"/dataset/xglue","name":"XGLUE","full_name":"","num_papers_in_archive":22},{"url":"/dataset/lince","name":"LinCE","full_name":"Linguistic Code-switching Evaluation Dataset","num_papers_in_archive":21},{"url":"/dataset/tweebank","name":"Tweebank","full_name":"","num_papers_in_archive":20},{"url":"/dataset/gum","name":"GUM","full_name":"Georgetown University Multilayer corpus","num_papers_in_archive":13},{"url":"/dataset/flue-french-language-understanding-evaluation","name":"FLUE","full_name":"French Language Understanding Evaluation","num_papers_in_archive":12},{"url":"/dataset/dane","name":"DaNE","full_name":"Danish Dependency Treebank","num_papers_in_archive":6},{"url":"/dataset/amalgum","name":"AMALGUM","full_name":"A Machine Annotated Lookalike of GUM","num_papers_in_archive":5},{"url":"/dataset/cuge","name":"CUGE","full_name":"","num_papers_in_archive":4},{"url":"/dataset/finer","name":"Finer","full_name":"Finnish News Corpus for Named Entity Recognition","num_papers_in_archive":4},{"url":"/dataset/szeged-corpus","name":"Szeged Corpus","full_name":"","num_papers_in_archive":4},{"url":"/dataset/alexa-point-of-view","name":"Alexa Point of View","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/antilles","name":"ANTILLES","full_name":"ANTILLES: An Open French Linguistically Enriched Part-of-Speech Corpus","num_papers_in_archive":1},{"url":"/dataset/conll-2017-shared-task-automatically","name":"CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings","full_name":"","num_papers_in_archive":1},{"url":"/dataset/egyptian-arabic-segmentation-dataset","name":"Egyptian Arabic Segmentation Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/igbonlp-datasets","name":"IgboNLP Datasets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/masc","name":"MASC","full_name":"Manually Annotated Sub-Corpus","num_papers_in_archive":1},{"url":"/dataset/morphosyntactic-analysis-dataset","name":"Morphosyntactic-analysis-dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ritter-pos","name":"Ritter PoS","full_name":"Ritter Twitter part-of-speech tagging","num_papers_in_archive":1},{"url":"/dataset/source-code-tagger-training-set","name":"Source Code Tagger Training Set","full_name":"","num_papers_in_archive":1},{"url":"/dataset/twitter-pos-vcb","name":"Twitter PoS VCB","full_name":"Twitter part-of-speech vote-constrained-bootstrapping","num_papers_in_archive":1},{"url":"/dataset/mac-morpho","name":"Mac-Morpho","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/unsupervised-part-of-speech-tagging","name":"Unsupervised Part-Of-Speech Tagging"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":10,"rows_per_page":100,"shown":100,"of":990,"of_with_code":228,"tagged_in_all":990,"counts":{"archive_papers_tagged":990,"with_a_code_link":228,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":990,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":6,"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"},"items":[{"url":"/paper/towards-deep-learning-models-resistant-to","slug":"towards-deep-learning-models-resistant-to","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","date":"2017-06-19","arxiv_id":"1706.06083","repositories_listed":59,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"9 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; 7 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/towards-deep-learning-models-resistant-to#ran","syntology_url":"https://syntology.ai/paper/1706.06083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.06083"}},"official":{"repos":["MadryLab/cifar10_challenge","MadryLab/mnist_challenge"],"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/end-to-end-sequence-labeling-via-bi","slug":"end-to-end-sequence-labeling-via-bi","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","date":"2016-03-04","arxiv_id":"1603.01354","repositories_listed":25,"syntology":{"n":24,"n_ran":24,"n_constructed":0,"n_ran_checked":22,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":20,"n_pointer_only":3,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-sequence-labeling-via-bi#ran","syntology_url":"https://syntology.ai/paper/1603.01354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.01354"}},"official":null}},{"url":"/paper/ask-me-anything-dynamic-memory-networks-for","slug":"ask-me-anything-dynamic-memory-networks-for","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","date":"2015-06-24","arxiv_id":"1506.07285","repositories_listed":10,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ask-me-anything-dynamic-memory-networks-for#ran","syntology_url":"https://syntology.ai/paper/1506.07285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.07285"}},"official":null}},{"url":"/paper/camembert-a-tasty-french-language-model","slug":"camembert-a-tasty-french-language-model","title":"CamemBERT: a Tasty French Language Model","date":"2019-11-10","arxiv_id":"1911.03894","repositories_listed":8,"syntology":null},{"url":"/paper/zen-pre-training-chinese-text-encoder","slug":"zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","arxiv_id":"1911.00720","repositories_listed":7,"syntology":{"n":35,"n_ran":28,"n_constructed":0,"n_ran_checked":22,"n_instrument":6,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":21,"n_pointer_only":2,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/zen-pre-training-chinese-text-encoder#ran","syntology_url":"https://syntology.ai/paper/1911.00720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00720"}},"official":{"repos":["sinovation/ZEN"],"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":["listed","official"]}}},{"url":"/paper/does-manipulating-tokenization-aid-cross","slug":"does-manipulating-tokenization-aid-cross","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","date":"2023-04-20","arxiv_id":"2304.10158","repositories_listed":6,"syntology":null},{"url":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","slug":"dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","repositories_listed":4,"syntology":{"n":3,"n_ran":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/dice-loss-for-data-imbalanced-nlp-tasks#ran","syntology_url":"https://syntology.ai/paper/1911.02855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02855"}},"official":{"repos":["ShannonAI/dice_loss_for_NLP"],"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/transfer-learning-for-sequence-tagging-with","slug":"transfer-learning-for-sequence-tagging-with","title":"Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks","date":"2017-03-18","arxiv_id":"1703.06345","repositories_listed":4,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transfer-learning-for-sequence-tagging-with#ran","syntology_url":"https://syntology.ai/paper/1703.06345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06345"}},"official":{"repos":["kimiyoung/transfer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/part-of-speech-tagging-with-bidirectional","slug":"part-of-speech-tagging-with-bidirectional","title":"Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network","date":"2015-10-21","arxiv_id":"1510.06168","repositories_listed":4,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/paper/beheshti-ner-persian-named-entity-recognition","slug":"beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","repositories_listed":3,"syntology":null},{"url":"/paper/generalizing-natural-language-analysis-1","slug":"generalizing-natural-language-analysis-1","title":"Generalizing Natural Language Analysis through Span-relation Representations","date":"2019-11-10","arxiv_id":"1911.03822","repositories_listed":3,"syntology":null},{"url":"/paper/ncrf-an-open-source-neural-sequence-labeling","slug":"ncrf-an-open-source-neural-sequence-labeling","title":"NCRF++: An Open-source Neural Sequence Labeling Toolkit","date":"2018-06-14","arxiv_id":"1806.05626","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ncrf-an-open-source-neural-sequence-labeling#ran","syntology_url":"https://syntology.ai/paper/1806.05626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05626"}},"official":{"repos":["jiesutd/NCRFpp"],"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/learning-approximate-inference-networks-for","slug":"learning-approximate-inference-networks-for","title":"Learning Approximate Inference Networks for Structured Prediction","date":"2018-03-09","arxiv_id":"1803.03376","repositories_listed":3,"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":1,"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/learning-approximate-inference-networks-for#ran","syntology_url":"https://syntology.ai/paper/1803.03376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03376"}},"official":null}},{"url":"/paper/empower-sequence-labeling-with-task-aware","slug":"empower-sequence-labeling-with-task-aware","title":"Empower Sequence Labeling with Task-Aware Neural Language Model","date":"2017-09-13","arxiv_id":"1709.04109","repositories_listed":3,"syntology":null},{"url":"/paper/semi-supervised-multitask-learning-for","slug":"semi-supervised-multitask-learning-for","title":"Semi-supervised Multitask Learning for Sequence Labeling","date":"2017-04-24","arxiv_id":"1704.07156","repositories_listed":3,"syntology":null},{"url":"/paper/multilingual-part-of-speech-tagging-with","slug":"multilingual-part-of-speech-tagging-with","title":"Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss","date":"2016-04-19","arxiv_id":"1604.05529","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multilingual-part-of-speech-tagging-with#ran","syntology_url":"https://syntology.ai/paper/1604.05529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.05529"}},"official":{"repos":["bplank/bilstm-aux"],"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":["listed","official"]}}},{"url":"/paper/pos-tagging-to-highlight-the-skeletal","slug":"pos-tagging-to-highlight-the-skeletal","title":"POS-tagging to highlight the skeletal structure of sentences","date":"2024-11-21","arxiv_id":"2411.14393","repositories_listed":2,"syntology":null},{"url":"/paper/lexically-grounded-subword-segmentation","slug":"lexically-grounded-subword-segmentation","title":"Lexically Grounded Subword Segmentation","date":"2024-06-19","arxiv_id":"2406.13560","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/lexically-grounded-subword-segmentation#ran","syntology_url":"https://syntology.ai/paper/2406.13560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13560"}},"official":{"repos":["ufal/legros","ufal/legros-paper"],"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":["official"]}}},{"url":"/paper/def2vec-extensible-word-embeddings-from","slug":"def2vec-extensible-word-embeddings-from","title":"Def2Vec: Extensible Word Embeddings from Dictionary Definitions","date":"2023-12-16","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/puoberta-training-and-evaluation-of-a-curated","slug":"puoberta-training-and-evaluation-of-a-curated","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","date":"2023-10-13","arxiv_id":"2310.09141","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-hungarian-text-processing-with","slug":"advancing-hungarian-text-processing-with","title":"Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines","date":"2023-08-24","arxiv_id":"2308.12635","repositories_listed":2,"syntology":null},{"url":"/paper/sentence-embedding-models-for-ancient-greek","slug":"sentence-embedding-models-for-ancient-greek","title":"Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation","date":"2023-08-24","arxiv_id":"2308.13116","repositories_listed":2,"syntology":null},{"url":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-boundary-aware-language-model","slug":"unsupervised-boundary-aware-language-model","title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","date":"2022-10-27","arxiv_id":"2210.15231","repositories_listed":2,"syntology":null},{"url":"/paper/reproducing-ner-and-pos-when-nothing-is","slug":"reproducing-ner-and-pos-when-nothing-is","title":"reproducing \"ner and pos when nothing is capitalized\"","date":"2021-09-17","arxiv_id":"2109.08396","repositories_listed":2,"syntology":null},{"url":"/paper/everything-is-all-it-takes-a-multipronged","slug":"everything-is-all-it-takes-a-multipronged","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","date":"2021-09-14","arxiv_id":"2109.06798","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/everything-is-all-it-takes-a-multipronged#ran","syntology_url":"https://syntology.ai/paper/2109.06798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06798"}},"official":{"repos":["shijie-wu/crosslingual-nlp","kentonmurray/arabicdetokenizer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/how-low-is-too-low-a-computational","slug":"how-low-is-too-low-a-computational","title":"How Low is Too Low? A Computational Perspective on Extremely Low-Resource Languages","date":"2021-05-30","arxiv_id":"2105.14515","repositories_listed":2,"syntology":null},{"url":"/paper/potential-idiomatic-expression-pie-english","slug":"potential-idiomatic-expression-pie-english","title":"Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms","date":"2021-04-25","arxiv_id":"2105.03280","repositories_listed":2,"syntology":null},{"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":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 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/graph-based-universal-dependency-parsing-in","slug":"graph-based-universal-dependency-parsing-in","title":"Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary","date":"2020-10-23","arxiv_id":"2010.12699","repositories_listed":2,"syntology":null},{"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/converting-the-point-of-view-of-messages","slug":"converting-the-point-of-view-of-messages","title":"Converting the Point of View of Messages Spoken to Virtual Assistants","date":"2020-10-06","arxiv_id":"2010.02600","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/what-s-so-special-about-bert-s-layers-a","slug":"what-s-so-special-about-bert-s-layers-a","title":"What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models","date":"2020-04-14","arxiv_id":"2004.06499","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/what-s-so-special-about-bert-s-layers-a#ran","syntology_url":"https://syntology.ai/paper/2004.06499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06499"}},"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":["official"]}}},{"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/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/omninet-a-unified-architecture-for-multi","slug":"omninet-a-unified-architecture-for-multi","title":"OmniNet: A unified architecture for multi-modal multi-task learning","date":"2019-07-17","arxiv_id":"1907.07804","repositories_listed":2,"syntology":null},{"url":"/paper/data-augmentation-via-dependency-tree-1","slug":"data-augmentation-via-dependency-tree-1","title":"Data Augmentation via Dependency Tree Morphing for Low-Resource Languages","date":"2019-03-22","arxiv_id":"1903.09460","repositories_listed":2,"syntology":null},{"url":"/paper/glyce-glyph-vectors-for-chinese-character","slug":"glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","arxiv_id":"1901.10125","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyce-glyph-vectors-for-chinese-character#ran","syntology_url":"https://syntology.ai/paper/1901.10125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10125"}},"official":{"repos":["ShannonAI/glyce"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/from-pos-tagging-to-dependency-parsing-for","slug":"from-pos-tagging-to-dependency-parsing-for","title":"From POS tagging to dependency parsing for biomedical event extraction","date":"2018-08-11","arxiv_id":"1808.03731","repositories_listed":2,"syntology":null},{"url":"/paper/lemmatag-jointly-tagging-and-lemmatizing-for","slug":"lemmatag-jointly-tagging-and-lemmatizing-for","title":"LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs","date":"2018-08-10","arxiv_id":"1808.03703","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/morphosyntactic-tagging-with-a-meta-bilstm","slug":"morphosyntactic-tagging-with-a-meta-bilstm","title":"Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings","date":"2018-05-21","arxiv_id":"1805.08237","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/strong-baselines-for-neural-semi-supervised","slug":"strong-baselines-for-neural-semi-supervised","title":"Strong Baselines for Neural Semi-supervised Learning under Domain Shift","date":"2018-04-25","arxiv_id":"1804.09530","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/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/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/step-by-step-instructions-and-a-simple","slug":"step-by-step-instructions-and-a-simple","title":"Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs","date":"2025-06-11","arxiv_id":"2506.09983","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/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/parsipy-nlp-toolkit-for-historical-persian","slug":"parsipy-nlp-toolkit-for-historical-persian","title":"ParsiPy: NLP Toolkit for Historical Persian Texts in Python","date":"2025-03-22","arxiv_id":"2503.17810","repositories_listed":1,"syntology":null},{"url":"/paper/gr-nlp-toolkit-an-open-source-nlp-toolkit-for","slug":"gr-nlp-toolkit-an-open-source-nlp-toolkit-for","title":"GR-NLP-TOOLKIT: An Open-Source NLP Toolkit for Modern Greek","date":"2024-12-11","arxiv_id":"2412.08520","repositories_listed":1,"syntology":null},{"url":"/paper/how-does-a-text-preprocessing-pipeline-affect","slug":"how-does-a-text-preprocessing-pipeline-affect","title":"How Does A Text Preprocessing Pipeline Affect Ontology Syntactic Matching?","date":"2024-11-06","arxiv_id":"2411.03962","repositories_listed":1,"syntology":null},{"url":"/paper/j2n-nominal-adjective-identification-and-its","slug":"j2n-nominal-adjective-identification-and-its","title":"J2N -- Nominal Adjective Identification and its Application","date":"2024-09-22","arxiv_id":"2409.14374","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-multi-granularity-tokenizer-for","slug":"multi-modal-multi-granularity-tokenizer-for","title":"Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts","date":"2024-09-02","arxiv_id":"2409.01011","repositories_listed":1,"syntology":null},{"url":"/paper/decomposed-meta-learning-for-few-shot","slug":"decomposed-meta-learning-for-few-shot","title":"Decomposed Meta-Learning for Few-Shot Sequence Labeling","date":"2024-03-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vnlp-turkish-nlp-package","slug":"vnlp-turkish-nlp-package","title":"VNLP: Turkish NLP Package","date":"2024-03-02","arxiv_id":"2403.01309","repositories_listed":1,"syntology":null},{"url":"/paper/drbenchmark-a-large-language-understanding","slug":"drbenchmark-a-large-language-understanding","title":"DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain","date":"2024-02-20","arxiv_id":"2402.13432","repositories_listed":1,"syntology":null},{"url":"/paper/punctuation-restoration-improves-structure","slug":"punctuation-restoration-improves-structure","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","date":"2024-02-13","arxiv_id":"2402.08382","repositories_listed":1,"syntology":null},{"url":"/paper/topro-token-level-prompt-decomposition-for","slug":"topro-token-level-prompt-decomposition-for","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","date":"2024-01-29","arxiv_id":"2401.16589","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-for-front-end-text","slug":"multi-task-learning-for-front-end-text","title":"Multi-Task Learning for Front-End Text Processing in TTS","date":"2024-01-12","arxiv_id":"2401.06321","repositories_listed":1,"syntology":null},{"url":"/paper/the-uncertainty-based-retrieval-framework-for-1","slug":"the-uncertainty-based-retrieval-framework-for-1","title":"The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS","date":"2023-10-12","arxiv_id":"2310.08496","repositories_listed":1,"syntology":null},{"url":"/paper/redpennet-for-grammatical-error-correction","slug":"redpennet-for-grammatical-error-correction","title":"RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to Spans","date":"2023-09-19","arxiv_id":"2309.10898","repositories_listed":1,"syntology":null},{"url":"/paper/discoverpath-a-knowledge-refinement-and","slug":"discoverpath-a-knowledge-refinement-and","title":"DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research","date":"2023-09-04","arxiv_id":"2309.01808","repositories_listed":1,"syntology":null},{"url":"/paper/fonmtl-towards-multitask-learning-for-the-fon","slug":"fonmtl-towards-multitask-learning-for-the-fon","title":"FonMTL: Towards Multitask Learning for the Fon Language","date":"2023-08-28","arxiv_id":"2308.14280","repositories_listed":1,"syntology":null},{"url":"/paper/mc-dre-multi-aspect-cross-integration-for","slug":"mc-dre-multi-aspect-cross-integration-for","title":"MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction","date":"2023-08-12","arxiv_id":"2308.06546","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cross-lingual-transfer-via-phonemic","slug":"enhancing-cross-lingual-transfer-via-phonemic","title":"Enhancing Cross-lingual Transfer via Phonemic Transcription Integration","date":"2023-07-10","arxiv_id":"2307.04361","repositories_listed":1,"syntology":null},{"url":"/paper/taqyim-evaluating-arabic-nlp-tasks-using","slug":"taqyim-evaluating-arabic-nlp-tasks-using","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","date":"2023-06-28","arxiv_id":"2306.16322","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/masakhapos-part-of-speech-tagging-for","slug":"masakhapos-part-of-speech-tagging-for","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages","date":"2023-05-23","arxiv_id":"2305.13989","repositories_listed":1,"syntology":null},{"url":"/paper/brent-bidirectional-retrieval-enhanced","slug":"brent-bidirectional-retrieval-enhanced","title":"BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer","date":"2023-04-19","arxiv_id":"2304.09649","repositories_listed":1,"syntology":null},{"url":"/paper/classification-of-us-supreme-court-cases","slug":"classification-of-us-supreme-court-cases","title":"Classification of US Supreme Court Cases using BERT-Based Techniques","date":"2023-04-17","arxiv_id":"2304.08649","repositories_listed":1,"syntology":null},{"url":"/paper/ancient-chinese-word-segmentation-and-part-of-1","slug":"ancient-chinese-word-segmentation-and-part-of-1","title":"Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision","date":"2023-03-03","arxiv_id":"2303.01912","repositories_listed":1,"syntology":null},{"url":"/paper/meeting-the-needs-of-low-resource-languages","slug":"meeting-the-needs-of-low-resource-languages","title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","date":"2023-02-15","arxiv_id":"2302.07912","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-true-potential-of-sequence-to","slug":"unleashing-the-true-potential-of-sequence-to","title":"Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing","date":"2023-02-05","arxiv_id":"2302.02275","repositories_listed":1,"syntology":null},{"url":"/paper/videberta-a-powerful-pre-trained-language","slug":"videberta-a-powerful-pre-trained-language","title":"ViDeBERTa: A powerful pre-trained language model for Vietnamese","date":"2023-01-25","arxiv_id":"2301.10439","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/videberta-a-powerful-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2301.10439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10439"}},"official":{"repos":["hysonlab/videberta"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-dataset-of-kurdish-sorani-named-entities-an","slug":"a-dataset-of-kurdish-sorani-named-entities-an","title":"A Dataset of Kurdish (Sorani) Named Entities -- An Amendment to Kurdish-BLARK Named Entities","date":"2023-01-12","arxiv_id":"2301.04962","repositories_listed":1,"syntology":null},{"url":"/paper/microbert-effective-training-of-low-resource","slug":"microbert-effective-training-of-low-resource","title":"MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning","date":"2022-12-23","arxiv_id":"2212.12510","repositories_listed":1,"syntology":null},{"url":"/paper/digicall-a-benchmark-for-measuring-the","slug":"digicall-a-benchmark-for-measuring-the","title":"DigiCall: A Benchmark for Measuring the Maturity of Digital Strategy through Company Earning Calls","date":"2022-12-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gnn-sl-sequence-labeling-based-on-nearest","slug":"gnn-sl-sequence-labeling-based-on-nearest","title":"GNN-SL: Sequence Labeling Based on Nearest Examples via GNN","date":"2022-12-05","arxiv_id":"2212.02017","repositories_listed":1,"syntology":null},{"url":"/paper/influence-functions-for-sequence-tagging","slug":"influence-functions-for-sequence-tagging","title":"Influence Functions for Sequence Tagging Models","date":"2022-10-25","arxiv_id":"2210.14177","repositories_listed":1,"syntology":null},{"url":"/paper/graph-based-multilingual-label-propagation","slug":"graph-based-multilingual-label-propagation","title":"Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging","date":"2022-10-18","arxiv_id":"2210.09840","repositories_listed":1,"syntology":null},{"url":"/paper/distillation-resistant-watermarking-for-model","slug":"distillation-resistant-watermarking-for-model","title":"Distillation-Resistant Watermarking for Model Protection in NLP","date":"2022-10-07","arxiv_id":"2210.03312","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/distillation-resistant-watermarking-for-model#ran","syntology_url":"https://syntology.ai/paper/2210.03312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03312"}},"official":{"repos":["xuandongzhao/drw"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-authoring-with-factual-english","slug":"knowledge-authoring-with-factual-english","title":"Knowledge Authoring with Factual English","date":"2022-08-05","arxiv_id":"2208.03094","repositories_listed":1,"syntology":null},{"url":"/paper/turkishdelightnlp-a-neural-turkish-nlp","slug":"turkishdelightnlp-a-neural-turkish-nlp","title":"TurkishDelightNLP: A Neural Turkish NLP Toolkit","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-stem-based-cross-lingual-part-of","slug":"unsupervised-stem-based-cross-lingual-part-of","title":"Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/building-an-endangered-language-resource-in","slug":"building-an-endangered-language-resource-in","title":"Building an Endangered Language Resource in the Classroom: Universal Dependencies for Kakataibo","date":"2022-06-21","arxiv_id":"2206.10343","repositories_listed":1,"syntology":null},{"url":"/paper/antilles-an-open-french-linguistically","slug":"antilles-an-open-french-linguistically","title":"ANTILLES: An Open French Linguistically Enriched Part-of-Speech Corpus","date":"2022-06-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-data-quality-and-quantity-for-a","slug":"pre-training-data-quality-and-quantity-for-a","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","date":"2022-05-21","arxiv_id":"2205.10517","repositories_listed":1,"syntology":null},{"url":"/paper/make-the-best-of-cross-lingual-transfer-1","slug":"make-the-best-of-cross-lingual-transfer-1","title":"Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-alignment-methods-for-ensemble","slug":"sequential-alignment-methods-for-ensemble","title":"Sequential Alignment Methods for Ensemble Part-of-Speech Tagging","date":"2022-03-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/g2pw-a-conditional-weighted-softmax-bert-for","slug":"g2pw-a-conditional-weighted-softmax-bert-for","title":"g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin","date":"2022-03-20","arxiv_id":"2203.10430","repositories_listed":1,"syntology":null},{"url":"/paper/annotating-the-tweebank-corpus-on-named","slug":"annotating-the-tweebank-corpus-on-named","title":"Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis","date":"2022-01-18","arxiv_id":"2201.07281","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":6,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 6 unverified","sample_list":"/paper/annotating-the-tweebank-corpus-on-named#ran","syntology_url":"https://syntology.ai/paper/2201.07281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.07281"}},"official":{"repos":["social-machines/tweebanknlp"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/distilling-the-knowledge-of-romanian-berts","slug":"distilling-the-knowledge-of-romanian-berts","title":"Distilling the Knowledge of Romanian BERTs Using Multiple Teachers","date":"2021-12-23","arxiv_id":"2112.12650","repositories_listed":1,"syntology":null},{"url":"/paper/transcouplet-transformer-based-chinese","slug":"transcouplet-transformer-based-chinese","title":"TransCouplet:Transformer based Chinese Couplet Generation","date":"2021-12-03","arxiv_id":"2112.01707","repositories_listed":1,"syntology":null},{"url":"/paper/a-coarse-to-fine-labeling-framework-for-joint","slug":"a-coarse-to-fine-labeling-framework-for-joint","title":"A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":19,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"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_where_code_ran":28,"papers_where_code_ran_first_page":"/task/part-of-speech-tagging/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":10,"url":"/task/part-of-speech-tagging/papers/2","json":"/task/part-of-speech-tagging/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/part-of-speech-tagging/papers/3","json":"/task/part-of-speech-tagging/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/part-of-speech-tagging/papers/4","json":"/task/part-of-speech-tagging/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/part-of-speech-tagging/papers/5","json":"/task/part-of-speech-tagging/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/part-of-speech-tagging/papers/6","json":"/task/part-of-speech-tagging/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/part-of-speech-tagging/papers/7","json":"/task/part-of-speech-tagging/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/part-of-speech-tagging/papers/8","json":"/task/part-of-speech-tagging/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/part-of-speech-tagging/papers/9","json":"/task/part-of-speech-tagging/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/part-of-speech-tagging/papers/10","json":"/task/part-of-speech-tagging/papers/10.json","rows":90},{"order":"ran","page":1,"of":1,"url":"/task/part-of-speech-tagging/papers/ran/1","json":"/task/part-of-speech-tagging/papers/ran/1.json","rows":28}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"56d0f812be5bbd302fdad4053416cb20a295a4c3ad72b006dd3ce948d1e1d316","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}