{"url":"/dataset/findvehicle","name":"FindVehicle","full_name":null,"description_markdown":"The ***first*** NER dataset in the field of traffic,  which is to extract the characteristics and attributes of the vehicle on the road.\r\n\r\n* Both flat and overlapped named entities annotation.\r\n* Both coarse-grained and fine-grained named entities.\r\n* It contains 8 kinds of coarse-grained entities and 12 kinds of fine-grained entities. (It includes 65 vehicle brands and 4793 vehicle models all over the world.)","description_withheld":null,"homepage":"https://github.com/GuanRunwei/FindVehicle","introduced_date":"2022-09-01","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC BY-NC","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"UIE","url":"/task/uie","datasets_with_task":"/datasets/task/uie"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FindVehicle"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-findvehicle","task":"Named Entity Recognition (NER)","dataset_variant":"FindVehicle","rows":3,"metrics":["F1 Score","F1"],"first_row_in_archive_order":{"model":"BiLSTM-CRF","paper":"/paper/bidirectional-lstm-crf-models-for-sequence","metrics":{"F1 Score":"49.5"},"code_links":[{"title":"determined22/zh-ner-tf","url":"https://github.com/determined22/zh-ner-tf"},{"title":"guillaumegenthial/tf_ner","url":"https://github.com/guillaumegenthial/tf_ner"},{"title":"baiyang2464/chatbot-base-on-Knowledge-Graph","url":"https://github.com/baiyang2464/chatbot-base-on-Knowledge-Graph"},{"title":"GlassyWing/bi-lstm-crf","url":"https://github.com/GlassyWing/bi-lstm-crf"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/lstm_crf"},{"title":"jidasheng/bi-lstm-crf","url":"https://github.com/jidasheng/bi-lstm-crf"},{"title":"aonotas/deep-crf","url":"https://github.com/aonotas/deep-crf"},{"title":"gxzzz/bilstm-crf","url":"https://github.com/gxzzz/bilstm-crf"},{"title":"epwalsh/pytorch-crf","url":"https://github.com/epwalsh/pytorch-crf"},{"title":"ngoquanghuy99/POS-Tagging-BiLSTM-CRF","url":"https://github.com/ngoquanghuy99/POS-Tagging-BiLSTM-CRF"},{"title":"HassanAzzam/Arabic-NER","url":"https://github.com/HassanAzzam/Arabic-NER"},{"title":"zysite/post","url":"https://github.com/zysite/post"},{"title":"DimasDMM/diseases-ner","url":"https://github.com/DimasDMM/diseases-ner"},{"title":"hazelnutsgz/Naive-LSTM-CRF","url":"https://github.com/hazelnutsgz/Naive-LSTM-CRF"},{"title":"kyzhouhzau/CCLNER","url":"https://github.com/kyzhouhzau/CCLNER"},{"title":"JZ-LIANG/CRF-LSTM-NER","url":"https://github.com/JZ-LIANG/CRF-LSTM-NER"},{"title":"moejoe95/crf-vs-rnn-ner","url":"https://github.com/moejoe95/crf-vs-rnn-ner"},{"title":"sarveshsparab/BiLSTMCRFSeqTag","url":"https://github.com/sarveshsparab/BiLSTMCRFSeqTag"},{"title":"sumehta/bilstm_crf_extract","url":"https://github.com/sumehta/bilstm_crf_extract"},{"title":"UcasLzz/ChineseWordSeg-POS","url":"https://github.com/UcasLzz/ChineseWordSeg-POS"},{"title":"Akshayanti/supersense-sequence-labelling","url":"https://github.com/Akshayanti/supersense-sequence-labelling"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/lstm_crf"},{"title":"UcasLzz/CWS","url":"https://github.com/UcasLzz/CWS"},{"title":"akshay-gupta123/BI-LSTM-CRF_Tensorflow","url":"https://github.com/akshay-gupta123/BI-LSTM-CRF_Tensorflow"},{"title":"2023-MindSpore-1/ms-code-5","url":"https://github.com/2023-MindSpore-1/ms-code-5/tree/main/lstm_crf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/uie-on-findvehicle","task":"UIE","dataset_variant":"FindVehicle","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"KnowCoder-7b-IE","paper":"/paper/knowcoder-coding-structured-knowledge-into","metrics":{"F1 score":"99.4"},"code_links":[{"title":"ICT-GoKnow/KnowCoder","url":"https://github.com/ICT-GoKnow/KnowCoder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":5,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/flert-document-level-features-for-named","title":"FLERT: Document-Level Features for Named Entity Recognition","date":"2020-11-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bidirectional-lstm-crf-models-for-sequence","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","date":"2015-08-09","rows_on_this_dataset":1,"code_links":25,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":20,"samples_ran":5,"samples_unverified":15,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}