{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/msra-cn-ner","name":"MSRA CN NER","full_name":"MSRA CN NER Dataset","description_markdown":"Simplified Chinese dataset for NER in The Third International Chinese Language Processing Bakeoff (2006), provided by Microsoft Research Asia (MSRA).","description_withheld":null,"homepage":"https://aclanthology.org/W06-0115/","introduced_date":"2006-07-01","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Cross-Lingual NER","url":"/task/cross-lingual-ner","datasets_with_task":"/datasets/task/cross-lingual-ner"},{"name":"Chinese Named Entity Recognition","url":"/task/chinese-named-entity-recognition","datasets_with_task":"/datasets/task/chinese-named-entity-recognition"},{"name":"Chinese Word Segmentation","url":"/task/chinese-word-segmentation","datasets_with_task":"/datasets/task/chinese-word-segmentation"},{"name":"NER","url":"/task/cg","datasets_with_task":"/datasets/task/cg"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MSRA","MSRA CN NER"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/chinese-named-entity-recognition-on-msra","task":"Chinese Named Entity Recognition","dataset_variant":"MSRA","rows":21,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"BERT-MRC+DSC","paper":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","metrics":{"F1":"96.72"},"code_links":[{"title":"ShannonAI/dice_loss_for_NLP","url":"https://github.com/ShannonAI/dice_loss_for_NLP"},{"title":"fursovia/self-adj-dice","url":"https://github.com/fursovia/self-adj-dice"},{"title":"MindCode-4/code-6","url":"https://github.com/MindCode-4/code-6/tree/main/drop-an-octave-reducing-spatial"},{"title":"MindCode-4/code-11","url":"https://github.com/MindCode-4/code-11/tree/main/dice-loss-for-data-imbalanced-nlp-tasks"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/chinese-word-segmentation-on-msra","task":"Chinese Word Segmentation","dataset_variant":"MSRA","rows":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"BABERT-LE","paper":"/paper/unsupervised-boundary-aware-language-model","metrics":{"F1":"98.63"},"code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/babert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-ner-on-msra","task":"Cross-Lingual NER","dataset_variant":"MSRA","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"Meta-Cross","paper":"/paper/enhanced-meta-learning-for-cross-lingual","metrics":{"F1":"77.89"},"code_links":[{"title":"microsoft/vert-papers","url":"https://github.com/microsoft/vert-papers/tree/master/papers/Meta-Cross"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":21,"of":21,"counts":{"papers_with_a_benchmark_row":21,"with_a_code_link":20,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":21,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/diffusionner-boundary-diffusion-for-named","slug":"diffusionner-boundary-diffusion-for-named","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","date":"2023-05-22","arxiv_id":"2305.13298","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/nflat-non-flat-lattice-transformer-for","slug":"nflat-non-flat-lattice-transformer-for","title":"NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition","date":"2022-05-12","arxiv_id":"2205.05832","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boundary-smoothing-for-named-entity-1","slug":"boundary-smoothing-for-named-entity-1","title":"Boundary Smoothing for Named Entity Recognition","date":"2022-04-26","arxiv_id":"2204.12031","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/parallel-instance-query-network-for-named","slug":"parallel-instance-query-network-for-named","title":"Parallel Instance Query Network for Named Entity Recognition","date":"2022-03-20","arxiv_id":"2203.10545","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-named-entity-recognition-as-word-word","slug":"unified-named-entity-recognition-as-word-word","title":"Unified Named Entity Recognition as Word-Word Relation Classification","date":"2021-12-19","arxiv_id":"2112.10070","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}}}},{"paper":"/paper/flat-chinese-ner-using-flat-lattice","slug":"flat-chinese-ner-using-flat-lattice","title":"FLAT: Chinese NER Using Flat-Lattice Transformer","date":"2020-04-24","arxiv_id":"2004.11795","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fgn-fusion-glyph-network-for-chinese-named","slug":"fgn-fusion-glyph-network-for-chinese-named","title":"FGN: Fusion Glyph Network for Chinese Named Entity Recognition","date":"2020-01-15","arxiv_id":"2001.05272","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhanced-meta-learning-for-cross-lingual","slug":"enhanced-meta-learning-for-cross-lingual","title":"Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources","date":"2019-11-14","arxiv_id":"1911.06161","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tener-adapting-transformer-encoder-for-name","slug":"tener-adapting-transformer-encoder-for-name","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","date":"2019-11-10","arxiv_id":"1911.04474","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["fastnlp/TENER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tener-adapting-transformer-encoder-for-name#ran","syntology_url":"https://syntology.ai/paper/1911.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04474"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":35,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":6,"samples_unverified":7,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/a-unified-mrc-framework-for-named-entity","slug":"a-unified-mrc-framework-for-named-entity","title":"A Unified MRC Framework for Named Entity Recognition","date":"2019-10-25","arxiv_id":"1910.11476","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["ShannonAI/mrc-for-flat-nested-ner"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-unified-mrc-framework-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/1910.11476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11476"}}}},{"paper":"/paper/simplify-the-usage-of-lexicon-in-chinese-ner","slug":"simplify-the-usage-of-lexicon-in-chinese-ner","title":"Simplify the Usage of Lexicon in Chinese NER","date":"2019-08-16","arxiv_id":"1908.05969","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["PaddlePaddle/ERNIE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}}}},{"paper":"/paper/ernie-enhanced-representation-through","slug":"ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-enhanced-representation-through#ran","syntology_url":"https://syntology.ai/paper/1904.09223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09223"}}}},{"paper":"/paper/can-ner-convolutional-attention-network","slug":"can-ner-convolutional-attention-network","title":"CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition","date":"2019-04-03","arxiv_id":"1904.02141","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/chinese-ner-using-lattice-lstm","slug":"chinese-ner-using-lattice-lstm","title":"Chinese NER Using Lattice LSTM","date":"2018-05-05","arxiv_id":"1805.02023","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["jiesutd/LatticeLSTM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chinese-ner-using-lattice-lstm#ran","syntology_url":"https://syntology.ai/paper/1805.02023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.02023"}}}},{"paper":"/paper/long-short-term-memory-neural-networks-for","slug":"long-short-term-memory-neural-networks-for","title":"Long Short-Term Memory Neural Networks for Chinese Word Segmentation","date":"2015-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/diffusionner-boundary-diffusion-for-named","slug":"diffusionner-boundary-diffusion-for-named","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","date":"2023-05-22","arxiv_id":"2305.13298","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/nflat-non-flat-lattice-transformer-for","slug":"nflat-non-flat-lattice-transformer-for","title":"NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition","date":"2022-05-12","arxiv_id":"2205.05832","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boundary-smoothing-for-named-entity-1","slug":"boundary-smoothing-for-named-entity-1","title":"Boundary Smoothing for Named Entity Recognition","date":"2022-04-26","arxiv_id":"2204.12031","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/parallel-instance-query-network-for-named","slug":"parallel-instance-query-network-for-named","title":"Parallel Instance Query Network for Named Entity Recognition","date":"2022-03-20","arxiv_id":"2203.10545","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-named-entity-recognition-as-word-word","slug":"unified-named-entity-recognition-as-word-word","title":"Unified Named Entity Recognition as Word-Word Relation Classification","date":"2021-12-19","arxiv_id":"2112.10070","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}}}},{"paper":"/paper/flat-chinese-ner-using-flat-lattice","slug":"flat-chinese-ner-using-flat-lattice","title":"FLAT: Chinese NER Using Flat-Lattice Transformer","date":"2020-04-24","arxiv_id":"2004.11795","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fgn-fusion-glyph-network-for-chinese-named","slug":"fgn-fusion-glyph-network-for-chinese-named","title":"FGN: Fusion Glyph Network for Chinese Named Entity Recognition","date":"2020-01-15","arxiv_id":"2001.05272","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhanced-meta-learning-for-cross-lingual","slug":"enhanced-meta-learning-for-cross-lingual","title":"Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources","date":"2019-11-14","arxiv_id":"1911.06161","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tener-adapting-transformer-encoder-for-name","slug":"tener-adapting-transformer-encoder-for-name","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","date":"2019-11-10","arxiv_id":"1911.04474","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["fastnlp/TENER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tener-adapting-transformer-encoder-for-name#ran","syntology_url":"https://syntology.ai/paper/1911.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04474"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":35,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":6,"samples_unverified":7,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/a-unified-mrc-framework-for-named-entity","slug":"a-unified-mrc-framework-for-named-entity","title":"A Unified MRC Framework for Named Entity Recognition","date":"2019-10-25","arxiv_id":"1910.11476","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["ShannonAI/mrc-for-flat-nested-ner"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-unified-mrc-framework-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/1910.11476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11476"}}}},{"paper":"/paper/simplify-the-usage-of-lexicon-in-chinese-ner","slug":"simplify-the-usage-of-lexicon-in-chinese-ner","title":"Simplify the Usage of Lexicon in Chinese NER","date":"2019-08-16","arxiv_id":"1908.05969","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["PaddlePaddle/ERNIE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}}}},{"paper":"/paper/ernie-enhanced-representation-through","slug":"ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-enhanced-representation-through#ran","syntology_url":"https://syntology.ai/paper/1904.09223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09223"}}}},{"paper":"/paper/can-ner-convolutional-attention-network","slug":"can-ner-convolutional-attention-network","title":"CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition","date":"2019-04-03","arxiv_id":"1904.02141","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/chinese-ner-using-lattice-lstm","slug":"chinese-ner-using-lattice-lstm","title":"Chinese NER Using Lattice LSTM","date":"2018-05-05","arxiv_id":"1805.02023","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["jiesutd/LatticeLSTM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chinese-ner-using-lattice-lstm#ran","syntology_url":"https://syntology.ai/paper/1805.02023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.02023"}}}},{"paper":"/paper/long-short-term-memory-neural-networks-for","slug":"long-short-term-memory-neural-networks-for","title":"Long Short-Term Memory Neural Networks for Chinese Word Segmentation","date":"2015-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/msra-cn-ner/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/msra-cn-ner/papers/ran/1","json":"/dataset/msra-cn-ner/papers/ran/1.json","rows":8}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":9,"samples_harvested":66,"samples_ran":55,"samples_constructed":0,"samples_ran_checked":45,"samples_ran_instrument_failed":10,"samples_unverified":11,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":8,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/chinese-named-entity-recognition-on-msra","since_archive":"/sota/chinese-named-entity-recognition-on-msra#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"5dd69d9ddc820ce549bfcebfe13cdda197b2d426d716c7f55f828e1b3ec2c1e4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}