{"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/token-classification","name":"Token Classification","slug":"token-classification","description_markdown":null,"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":100,"papers_with_code":47,"benchmarks":0,"benchmark_tables_in_archive":18,"benchmark_tables_shown":18,"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":15,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":null,"slug":"token-classification-on-conll2002","dataset":"conll2002","dataset_url":"/dataset/conll-2002","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-conll2003","dataset":"conll2003","dataset_url":"/dataset/conll-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall","loss"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-doc-lay-net-small","dataset":"doc_lay_net-small","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-grit-id-id-nergrit","dataset":"grit-id/id_nergrit_corpus ner","dataset_url":"/dataset/nergrit-corpus","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-indonlu","dataset":"indonlu","dataset_url":"/dataset/indonlu-benchmark","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-ingredients-yes-no","dataset":"ingredients_yes_no","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-invoice","dataset":"Invoice","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-lener-br","dataset":"lener_br","dataset_url":"/dataset/lener-br","rows_in_archive":0,"metrics":["Accuracy","F1","Loss","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-mim-gold-ner","dataset":"mim_gold_ner","dataset_url":"/dataset/mim-gold-ner-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-nielsr-funsd","dataset":"nielsr/funsd-layoutlmv3","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-openfoodfacts","dataset":"openfoodfacts/nutrient-detection-layout","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-peoples-daily-ner","dataset":"peoples_daily_ner","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-sroie","dataset":"SROIE","dataset_url":"/dataset/sroie","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-turkish-ner","dataset":"turkish_ner","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-wikiann","dataset":"Wikiann","dataset_url":"/dataset/wikiann-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-wikiann-sk-1","dataset":"wikiann sk","dataset_url":"/dataset/wikiann-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-x-glue","dataset":"x_glue","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-xtreme","dataset":"XTREME","dataset_url":"/dataset/xtreme","rows_in_archive":0,"metrics":["F1"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/conll-2003","name":"CoNLL 2003","full_name":"","num_papers_in_archive":755},{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/sroie","name":"SROIE","full_name":"","num_papers_in_archive":105},{"url":"/dataset/wikiann-1","name":"WikiANN","full_name":"PAN-X","num_papers_in_archive":72},{"url":"/dataset/conll-2002","name":"CoNLL 2002","full_name":"","num_papers_in_archive":70},{"url":"/dataset/xtreme","name":"XTREME","full_name":"Cross-Lingual Transfer Evaluation of Multilingual Encoders","num_papers_in_archive":55},{"url":"/dataset/indonlu-benchmark","name":"IndoNLU Benchmark","full_name":"","num_papers_in_archive":14},{"url":"/dataset/wikineural","name":"WikiNEuRal","full_name":"","num_papers_in_archive":6},{"url":"/dataset/lener-br","name":"LeNER-Br","full_name":"","num_papers_in_archive":3},{"url":"/dataset/geoedda","name":"GeoEDdA","full_name":"A Gold Standard Dataset for Geo-semantic Annotation of Diderot & d’Alembert’s Encyclopédie","num_papers_in_archive":1},{"url":"/dataset/russian-sntences-pos-taggeds","name":"Russian Sentences POS tagged","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mim-gold-ner-1","name":"MIM-GOLD-NER","full_name":"","num_papers_in_archive":0},{"url":"/dataset/nergrit-corpus","name":"NERGRIT Corpus","full_name":"","num_papers_in_archive":0},{"url":"/dataset/ud-tagalog-newscrawl","name":"UD_Tagalog-NewsCrawl","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/blackout-poetry-generation","name":"Blackout Poetry Generation"},{"url":"/task/toxic-spans-detection","name":"Toxic Spans Detection"}],"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":1,"rows_per_page":100,"shown":100,"of":100,"of_with_code":47,"tagged_in_all":100,"counts":{"archive_papers_tagged":100,"with_a_code_link":47,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":100,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/lettucedetect-a-hallucination-detection","slug":"lettucedetect-a-hallucination-detection","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","date":"2025-02-24","arxiv_id":"2502.17125","repositories_listed":2,"syntology":null},{"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/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 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/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","slug":"reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/towards-populating-generalizable-engineering","slug":"towards-populating-generalizable-engineering","title":"Retrieval Augmented Generation using Engineering Design Knowledge","date":"2023-07-13","arxiv_id":"2307.06985","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/detecting-label-errors-in-token","slug":"detecting-label-errors-in-token","title":"Detecting Label Errors in Token Classification Data","date":"2022-10-08","arxiv_id":"2210.03920","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/detecting-label-errors-in-token#ran","syntology_url":"https://syntology.ai/paper/2210.03920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03920"}},"official":{"repos":["cleanlab/cleanlab","cleanlab/token-label-error-benchmarks"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wangchanberta-pretraining-transformer-based","slug":"wangchanberta-pretraining-transformer-based","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","date":"2021-01-24","arxiv_id":"2101.09635","repositories_listed":2,"syntology":null},{"url":"/paper/the-devil-is-in-the-word-alignment-details-on","slug":"the-devil-is-in-the-word-alignment-details-on","title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","date":"2025-05-15","arxiv_id":"2505.10507","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-next-token-next-x-prediction-for","slug":"beyond-next-token-next-x-prediction-for","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","date":"2025-02-27","arxiv_id":"2502.20388","repositories_listed":1,"syntology":null},{"url":"/paper/autotrain-no-code-training-for-state-of-the","slug":"autotrain-no-code-training-for-state-of-the","title":"AutoTrain: No-code training for state-of-the-art models","date":"2024-10-21","arxiv_id":"2410.15735","repositories_listed":1,"syntology":null},{"url":"/paper/chulo-chunk-level-key-information","slug":"chulo-chunk-level-key-information","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Processing","date":"2024-10-14","arxiv_id":"2410.11119","repositories_listed":1,"syntology":null},{"url":"/paper/gus-net-social-bias-classification-in-text","slug":"gus-net-social-bias-classification-in-text","title":"GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes","date":"2024-10-10","arxiv_id":"2410.08388","repositories_listed":1,"syntology":null},{"url":"/paper/acquiring-bidirectionality-via-large-and","slug":"acquiring-bidirectionality-via-large-and","title":"Acquiring Bidirectionality via Large and Small Language Models","date":"2024-08-19","arxiv_id":"2408.09640","repositories_listed":1,"syntology":null},{"url":"/paper/mememind-at-araieval-shared-task-spotting","slug":"mememind-at-araieval-shared-task-spotting","title":"MemeMind at ArAIEval Shared Task: Spotting Persuasive Spans in Arabic Text with Persuasion Techniques Identification","date":"2024-08-08","arxiv_id":"2408.04540","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01063","slug":"2408-01063","title":"Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction","date":"2024-08-02","arxiv_id":"2408.01063","repositories_listed":1,"syntology":null},{"url":"/paper/deep-content-understanding-toward-entity-and","slug":"deep-content-understanding-toward-entity-and","title":"Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation Models","date":"2024-07-04","arxiv_id":"2407.04050","repositories_listed":1,"syntology":null},{"url":"/paper/what-s-mine-becomes-yours-defining-annotating","slug":"what-s-mine-becomes-yours-defining-annotating","title":"What's Mine becomes Yours: Defining, Annotating and Detecting Context-Dependent Paraphrases in News Interview Dialogs","date":"2024-04-10","arxiv_id":"2404.06670","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-shortest-edit-script-methods-for","slug":"evaluating-shortest-edit-script-methods-for","title":"Evaluating Shortest Edit Script Methods for Contextual Lemmatization","date":"2024-03-25","arxiv_id":"2403.16968","repositories_listed":1,"syntology":null},{"url":"/paper/llmlingua-2-data-distillation-for-efficient","slug":"llmlingua-2-data-distillation-for-efficient","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","date":"2024-03-19","arxiv_id":"2403.12968","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/entity-or-relation-embeddings-an-analysis-of","slug":"entity-or-relation-embeddings-an-analysis-of","title":"Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction","date":"2023-12-18","arxiv_id":"2312.11062","repositories_listed":1,"syntology":null},{"url":"/paper/lazy-k-decoding-for-constrained-token","slug":"lazy-k-decoding-for-constrained-token","title":"Lazy-k: Decoding for Constrained Token Classification","date":"2023-12-06","arxiv_id":"2312.03367","repositories_listed":1,"syntology":null},{"url":"/paper/one-for-all-all-for-one-bypassing","slug":"one-for-all-all-for-one-bypassing","title":"One For All & All For One: Bypassing Hyperparameter Tuning with Model Averaging For Cross-Lingual Transfer","date":"2023-10-16","arxiv_id":"2310.10532","repositories_listed":1,"syntology":null},{"url":"/paper/free-lunch-robust-cross-lingual-transfer-via","slug":"free-lunch-robust-cross-lingual-transfer-via","title":"Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging","date":"2023-05-26","arxiv_id":"2305.16834","repositories_listed":1,"syntology":null},{"url":"/paper/a-transformer-based-method-for-zero-and-few","slug":"a-transformer-based-method-for-zero-and-few","title":"From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts","date":"2023-05-05","arxiv_id":"2305.04928","repositories_listed":1,"syntology":null},{"url":"/paper/classbases-at-case-2022-multilingual-protest","slug":"classbases-at-case-2022-multilingual-protest","title":"ClassBases at CASE-2022 Multilingual Protest Event Detection Tasks: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets","date":"2023-01-16","arxiv_id":"2301.06617","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-the-fact-checkers-automatic","slug":"empowering-the-fact-checkers-automatic","title":"Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter","date":"2022-10-10","arxiv_id":"2210.04710","repositories_listed":1,"syntology":null},{"url":"/paper/improving-radiology-report-generation-systems","slug":"improving-radiology-report-generation-systems","title":"Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors","date":"2022-09-27","arxiv_id":"2210.06340","repositories_listed":1,"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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-radiology-report-generation-systems#ran","syntology_url":"https://syntology.ai/paper/2210.06340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06340"}},"official":{"repos":["rajpurkarlab/cxr-redone"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/namedentityrangers-at-semeval-2022-task-11","slug":"namedentityrangers-at-semeval-2022-task-11","title":"NamedEntityRangers at SemEval-2022 Task 11: Transformer-based Approaches for Multilingual Complex Named Entity Recognition","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/general-and-domain-adaptive-chinese-spelling","slug":"general-and-domain-adaptive-chinese-spelling","title":"General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining","date":"2022-03-21","arxiv_id":"2203.10929","repositories_listed":1,"syntology":null},{"url":"/paper/uob-at-semeval-2021-task-5-extending-pre-1","slug":"uob-at-semeval-2021-task-5-extending-pre-1","title":"UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction","date":"2021-10-07","arxiv_id":"2110.03730","repositories_listed":1,"syntology":null},{"url":"/paper/bert-got-a-date-introducing-transformers-to","slug":"bert-got-a-date-introducing-transformers-to","title":"BERT got a Date: Introducing Transformers to Temporal Tagging","date":"2021-09-30","arxiv_id":"2109.14927","repositories_listed":1,"syntology":null},{"url":"/paper/entity-at-semeval-2021-task-5-weakly","slug":"entity-at-semeval-2021-task-5-weakly","title":"Entity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/youngsheldon-at-semeval-2021-task-5-fine","slug":"youngsheldon-at-semeval-2021-task-5-fine","title":"YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ultrasound-video-transformers-for-cardiac","slug":"ultrasound-video-transformers-for-cardiac","title":"Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation","date":"2021-07-02","arxiv_id":"2107.00977","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-visual-layout-structures-for","slug":"incorporating-visual-layout-structures-for","title":"VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups","date":"2021-06-01","arxiv_id":"2106.00676","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/incorporating-visual-layout-structures-for#ran","syntology_url":"https://syntology.ai/paper/2106.00676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00676"}},"official":{"repos":["allenai/VILA"],"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/nlrg-at-semeval-2021-task-5-toxic-spans","slug":"nlrg-at-semeval-2021-task-5-toxic-spans","title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","date":"2021-02-24","arxiv_id":"2102.12254","repositories_listed":1,"syntology":null},{"url":"/paper/domino-at-fincausal-2020-task-1-and-2-causal","slug":"domino-at-fincausal-2020-task-1-and-2-causal","title":"Domino at FinCausal 2020, Task 1 and 2: Causal Extraction System","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/indic-transformers-an-analysis-of-transformer","slug":"indic-transformers-an-analysis-of-transformer","title":"Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages","date":"2020-11-04","arxiv_id":"2011.02323","repositories_listed":1,"syntology":null},{"url":"/paper/on-long-tailed-phenomena-in-neural-machine","slug":"on-long-tailed-phenomena-in-neural-machine","title":"On Long-Tailed Phenomena in Neural Machine Translation","date":"2020-10-10","arxiv_id":"2010.04924","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-long-tailed-phenomena-in-neural-machine#ran","syntology_url":"https://syntology.ai/paper/2010.04924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04924"}},"official":{"repos":["vyraun/long-tailed"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-detection-meets-transfer","slug":"counterfactual-detection-meets-transfer","title":"Counterfactual Detection meets Transfer Learning","date":"2020-05-27","arxiv_id":"2005.13125","repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-syntactic-features-helps","slug":"joint-learning-of-syntactic-features-helps","title":"Joint Learning of Syntactic Features Helps Discourse Segmentation","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/common-knowledge-concept-recognition-for-seva","slug":"common-knowledge-concept-recognition-for-seva","title":"Common-Knowledge Concept Recognition for SEVA","date":"2020-03-26","arxiv_id":"2003.11687","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-entity-knowledge-in-bert-with-1","slug":"investigating-entity-knowledge-in-bert-with-1","title":"Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking","date":"2020-03-11","arxiv_id":"2003.05473","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/investigating-entity-knowledge-in-bert-with-1#ran","syntology_url":"https://syntology.ai/paper/2003.05473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05473"}},"official":{"repos":["samuelbroscheit/entity_knowledge_in_bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"nested-named-entity-recognition-as-single","title":"Nested Named Entity Recognition as Single-Pass Sequence Labeling","date":"2025-05-22","arxiv_id":"2505.16855","repositories_listed":0,"syntology":null},{"url":null,"slug":"mooscomp-improving-lightweight-long-context","title":"MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores","date":"2025-04-23","arxiv_id":"2504.16786","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-and-fine-grained-detection-of-ai","title":"Robust and Fine-Grained Detection of AI Generated Texts","date":"2025-04-16","arxiv_id":"2504.11952","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-applicability-of-deep-learning","title":"Improving Applicability of Deep Learning based Token Classification models during Training","date":"2025-03-28","arxiv_id":"2504.01028","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-language-of-nvme-streams-for","title":"Learning the Language of NVMe Streams for Ransomware Detection","date":"2025-02-07","arxiv_id":"2502.05011","repositories_listed":0,"syntology":null},{"url":null,"slug":"glilem-leveraging-gliner-for-contextualized","title":"GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian","date":"2024-12-29","arxiv_id":"2412.20597","repositories_listed":0,"syntology":null},{"url":null,"slug":"bangla-grammatical-error-detection-leveraging","title":"Bangla Grammatical Error Detection Leveraging Transformer-based Token Classification","date":"2024-11-13","arxiv_id":"2411.08344","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidora-bi-level-optimization-based-weight","title":"BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation","date":"2024-10-13","arxiv_id":"2410.09758","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-the-capabilities-of-compact-models","title":"Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation","date":"2024-10-01","arxiv_id":"2410.00387","repositories_listed":0,"syntology":null},{"url":null,"slug":"taco-rl-task-aware-prompt-compression","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","date":"2024-09-19","arxiv_id":"2409.13035","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-empirical-probabilities-in-bert","title":"Preserving Empirical Probabilities in BERT for Small-sample Clinical Entity Recognition","date":"2024-09-05","arxiv_id":"2409.03238","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-merit-dataset-modelling-and-efficiently","title":"The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts","date":"2024-08-31","arxiv_id":"2409.00447","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-extraction-for-portuguese-a-qa-driven","title":"Event Extraction for Portuguese: A QA-driven Approach using ACE-2005","date":"2024-08-29","arxiv_id":"2408.16932","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-dualchecker-for-mitigating","title":"Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models","date":"2024-08-22","arxiv_id":"2408.12326","repositories_listed":0,"syntology":null},{"url":null,"slug":"looks-can-be-deceptive-distinguishing","title":"Looks can be Deceptive: Distinguishing Repetition Disfluency from Reduplication","date":"2024-07-11","arxiv_id":"2407.08147","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-on-a-budget-a-case-study","title":"In-Context Learning on a Budget: A Case Study in Token Classification","date":"2024-06-19","arxiv_id":"2406.13274","repositories_listed":0,"syntology":null},{"url":"/paper/beads-bias-evaluation-across-domains","slug":"beads-bias-evaluation-across-domains","title":"BEADs: Bias Evaluation Across Domains","date":"2024-06-06","arxiv_id":"2406.04220","repositories_listed":0,"syntology":null},{"url":null,"slug":"gentoc-leveraging-partially-labeled-data-for","title":"A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification","date":"2024-05-17","arxiv_id":"2405.10918","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-extraction-in-basque-typologically","title":"Event Extraction in Basque: Typologically motivated Cross-Lingual Transfer-Learning Analysis","date":"2024-04-09","arxiv_id":"2404.06392","repositories_listed":0,"syntology":null},{"url":null,"slug":"tm-trek-at-semeval-2024-task-8-towards-llm","title":"TM-TREK at SemEval-2024 Task 8: Towards LLM-Based Automatic Boundary Detection for Human-Machine Mixed Text","date":"2024-04-01","arxiv_id":"2404.00899","repositories_listed":0,"syntology":null},{"url":null,"slug":"ignore-me-but-don-t-replace-me-utilizing-non","title":"Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain","date":"2024-03-15","arxiv_id":"2403.10576","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-weight-experiments-for-llm-instruction","title":"Instruction Fine-Tuning: Does Prompt Loss Matter?","date":"2024-01-24","arxiv_id":"2401.13586","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-text-diacritization-in-the-age-of","title":"Arabic Text Diacritization In The Age Of Transfer Learning: Token Classification Is All You Need","date":"2024-01-09","arxiv_id":"2401.04848","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-supertagging-for-hpsg","title":"Revisiting Supertagging for Faster HPSG Pasing","date":"2023-09-14","arxiv_id":"2309.07590","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-spells-in-fantasy-literature-with-a","title":"Detecting Spells in Fantasy Literature with a Transformer Based Artificial Intelligence","date":"2023-08-07","arxiv_id":"2308.03660","repositories_listed":0,"syntology":null},{"url":null,"slug":"nbias-a-natural-language-processing-framework","title":"NBIAS: A Natural Language Processing Framework for Bias Identification in Text","date":"2023-08-03","arxiv_id":"2308.01681","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-document-analytics-for-banking","title":"Multimodal Document Analytics for Banking Process Automation","date":"2023-07-21","arxiv_id":"2307.11845","repositories_listed":0,"syntology":null},{"url":null,"slug":"people-and-places-of-historical-europe","title":"People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts","date":"2023-05-26","arxiv_id":"2305.16718","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-free-data-efficient-multilingual","title":"Transfer-Free Data-Efficient Multilingual Slot Labeling","date":"2023-05-22","arxiv_id":"2305.13528","repositories_listed":0,"syntology":null},{"url":null,"slug":"persian-typographical-error-type-detection","title":"Persian Typographical Error Type Detection Using Deep Neural Networks on Algorithmically-Generated Misspellings","date":"2023-05-19","arxiv_id":"2305.11731","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-variation-in-tokenizer-outputs","title":"Comparing Variation in Tokenizer Outputs Using a Series of Problematic and Challenging Biomedical Sentences","date":"2023-05-15","arxiv_id":"2305.08787","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-extraction-from-documents","title":"Information Extraction from Documents: Question Answering vs Token Classification in real-world setups","date":"2023-04-21","arxiv_id":"2304.10994","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-study-between-token-classification","title":"Comparison Study Between Token Classification and Sequence Classification In Text Classification","date":"2022-11-25","arxiv_id":"2211.13899","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-text-pre-training-with-extended-token","title":"Short Text Pre-training with Extended Token Classification for E-commerce Query Understanding","date":"2022-10-08","arxiv_id":"2210.03915","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-classification-for-disambiguating","title":"Token Classification for Disambiguating Medical Abbreviations","date":"2022-10-05","arxiv_id":"2210.02487","repositories_listed":0,"syntology":null},{"url":null,"slug":"john-snow-labs-smm4h22-social-media-mining","title":"John_Snow_Labs@SMM4H’22: Social Media Mining for Health (#SMM4H) with Spark NLP","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tradeoffs-in-resampling-and-filtering-for","title":"Tradeoffs in Resampling and Filtering for Imbalanced Classification","date":"2022-08-31","arxiv_id":"2209.00127","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-three-types-of-embeddings-from","title":"Leveraging Three Types of Embeddings from Masked Language Models in Idiom Token Classification","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-coarse-grained-data-in-low-data","title":"Utilizing coarse-grained data in low-data settings for event extraction","date":"2022-05-11","arxiv_id":"2205.05468","repositories_listed":0,"syntology":null},{"url":null,"slug":"region-dependent-temperature-scaling-for","title":"Region-dependent temperature scaling for certainty calibration and application to class-imbalanced token classification","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"um6p-cs-at-semeval-2022-task-11-enhancing","title":"UM6P-CS at SemEval-2022 Task 11: Enhancing Multilingual and Code-Mixed Complex Named Entity Recognition via Pseudo Labels using Multilingual Transformer","date":"2022-04-28","arxiv_id":"2204.13515","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bit-bayesian-facilitates-efficient-training","title":"A Bit Bayesian Facilitates Efficient Training in Token Classification","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-got-a-date-introducing-transformers-to-1","title":"BERT got a Date: Introducing Transformers to Temporal Tagging","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ecspell-ud-zero-shot-domain-adaptive-chinese","title":"ECSpell$^{UD}$: Zero-shot Domain Adaptive Chinese Spelling Check with User Dictionary","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seqattack-on-adversarial-attacks-for-named","title":"SeqAttack: On Adversarial Attacks for Named Entity Recognition","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sesame-street-to-mount-sinai-bert-constrained","title":"Sesame Street to Mount Sinai: BERT-constrained character-level Moses models for multilingual lexical normalization","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"de-identification-of-unstructured-clinical","title":"De-identification of Unstructured Clinical Texts from Sequence to Sequence Perspective","date":"2021-08-18","arxiv_id":"2108.07971","repositories_listed":0,"syntology":null},{"url":null,"slug":"ghost-at-semeval-2021-task-5-is-explanation","title":"GHOST at SemEval-2021 Task 5: Is explanation all you need?","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-cleaning-tools-for-token-classification","title":"Data Cleaning Tools for Token Classification Tasks","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multivitaminbooster-at-parseme-shared-task","title":"MultiVitaminBooster at PARSEME Shared Task 2020: Combining Window- and Dependency-Based Features with Multilingual Contextualised Word Embeddings for VMWE Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-input-representation-for-language","title":"Evaluating Input Representation for Language Identification in Hindi-English Code Mixed Text","date":"2020-11-23","arxiv_id":"2011.11263","repositories_listed":0,"syntology":null},{"url":null,"slug":"idiom-token-classification-using-sentential","title":"Idiom Token Classification using Sentential Distributed Semantics","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-resources-for-mwe-token","title":"Combining resources for MWE-token classification","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":6,"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":6,"papers_where_code_ran_first_page":"/task/token-classification/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":"ran","page":1,"of":1,"url":"/task/token-classification/papers/ran/1","json":"/task/token-classification/papers/ran/1.json","rows":6}],"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":"08b1a6a668644ae52b18cfe5afb4560a97107a9eb93007f5f3dcc056263ef41c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}