{"url":"/sota/paraphrase-identification-on-quora-question","task":{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","note":null},"dataset":{"name":"Quora Question Pairs","url":"/dataset/quora-question-pairs"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"The goal of **Paraphrase Identification** is to determine whether a pair of sentences have the same meaning.\r\n\r\n\r\n<span class=\"description-source\">Source: [Adversarial Examples with Difficult Common Words for Paraphrase Identification ](https://arxiv.org/abs/1909.02560)</span>\r\n\r\nImage source: [On Paraphrase Identification Corpora ](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1000_Paper.pdf)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1","Accuracy","Direct Intrinsic Dimension","Structure Aware Intrinsic Dimension","Dev Accuracy","Accuarcy","Dev F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher","Accuracy":"higher","Direct Intrinsic Dimension":null,"Structure Aware Intrinsic Dimension":null,"Dev Accuracy":"higher","Accuarcy":null,"Dev F1":"higher"}},"counts":{"rows":31,"rows_with_code":26,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ALICE","metrics":{"F1":"90.7"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"RoBERTa-large 355M + Entailment as Few-shot Learner","metrics":{"F1":"89.2"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/entailment-as-few-shot-learner","paper_url":"https://arxiv.org/abs/2104.14690v1","paper_title":"Entailment as Few-Shot Learner","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/efl","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Charformer-Tall","metrics":{"Accuracy":"91.4","F1":"88.5"},"uses_additional_data":false,"paper_date":"2021-06-23","paper":"/paper/charformer-fast-character-transformers-via","paper_url":"https://arxiv.org/abs/2106.12672v3","paper_title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"RealFormer","metrics":{"Accuracy":"91.34","F1":"88.28"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/informer-transformer-likes-informed-attention","paper_url":"https://arxiv.org/abs/2012.11747v3","paper_title":"RealFormer: Transformer Likes Residual Attention","code":"https://github.com/google-research/google-research","n_code_links":5,"syntology":null},{"rank_in_archive_order":5,"model":"FNet-Large","metrics":{"F1":"85"},"uses_additional_data":false,"paper_date":"2021-05-09","paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","paper_url":"https://arxiv.org/abs/2105.03824v4","paper_title":"FNet: Mixing Tokens with Fourier Transforms","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":12,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"StructBERTRoBERTa ensemble","metrics":{"Accuracy":"90.7","F1":"74.4"},"uses_additional_data":false,"paper_date":"2019-08-13","paper":"/paper/structbert-incorporating-language-structures","paper_url":"https://arxiv.org/abs/1908.04577v3","paper_title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"XLNet-Large (ensemble)","metrics":{"Accuracy":"90.3","F1":"74.2"},"uses_additional_data":false,"paper_date":"2019-06-19","paper":"/paper/xlnet-generalized-autoregressive-pretraining","paper_url":"https://arxiv.org/abs/1906.08237v2","paper_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":27,"syntology":{"n_ran":10,"n_unverified":14,"n_samples":24,"n_pointer_only_licence":3}},{"rank_in_archive_order":8,"model":"ASA + RoBERTa","metrics":{"F1":"73.7"},"uses_additional_data":false,"paper_date":"2022-06-25","paper":"/paper/adversarial-self-attention-for-language","paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","code":"https://github.com/gingasan/adversarialsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Snorkel MeTaL(ensemble)","metrics":{"Accuracy":"89.9","F1":"73.1"},"uses_additional_data":false,"paper_date":"2018-10-05","paper":"/paper/training-complex-models-with-multi-task-weak","paper_url":"http://arxiv.org/abs/1810.02840v2","paper_title":"Training Complex Models with Multi-Task Weak Supervision","code":"https://github.com/HazyResearch/metal","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"MT-DNN","metrics":{"Accuracy":"89.6","F1":"72.4"},"uses_additional_data":false,"paper_date":"2019-01-31","paper":"/paper/multi-task-deep-neural-networks-for-natural","paper_url":"https://arxiv.org/abs/1901.11504v2","paper_title":"Multi-Task Deep Neural Networks for Natural Language Understanding","code":"https://github.com/namisan/mt-dnn","n_code_links":7,"syntology":{"n_ran":7,"n_unverified":6,"n_samples":13,"n_pointer_only_licence":2}},{"rank_in_archive_order":11,"model":"ASA + BERT-base","metrics":{"F1":"72.3"},"uses_additional_data":false,"paper_date":"2022-06-25","paper":"/paper/adversarial-self-attention-for-language","paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","code":"https://github.com/gingasan/adversarialsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"BERT-LARGE","metrics":{"F1":"72.1"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"syntology":{"n_ran":208,"n_unverified":451,"n_samples":659,"n_pointer_only_licence":149}},{"rank_in_archive_order":13,"model":"SpanBERT","metrics":{"Accuracy":"89.5","F1":"71.9"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/spanbert-improving-pre-training-by","paper_url":"https://arxiv.org/abs/1907.10529v3","paper_title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","code":"https://github.com/facebookresearch/SpanBERT","n_code_links":6,"syntology":{"n_ran":6,"n_unverified":9,"n_samples":15,"n_pointer_only_licence":4}},{"rank_in_archive_order":14,"model":"TinyBERT","metrics":{"F1":"71.3"},"uses_additional_data":false,"paper_date":"2019-09-23","paper":"/paper/190910351","paper_url":"https://arxiv.org/abs/1909.10351v5","paper_title":"TinyBERT: Distilling BERT for Natural Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":15,"model":"ERNIE","metrics":{"F1":"71.2"},"uses_additional_data":false,"paper_date":"2019-05-17","paper":"/paper/ernie-enhanced-language-representation-with","paper_url":"https://arxiv.org/abs/1905.07129v3","paper_title":"ERNIE: Enhanced Language Representation with Informative Entities","code":"https://github.com/thunlp/ERNIE","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"data2vec","metrics":{"Accuracy":"92.4"},"uses_additional_data":false,"paper_date":"2022-02-07","paper":"/paper/data2vec-a-general-framework-for-self-1","paper_url":"https://arxiv.org/abs/2202.03555v3","paper_title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","code":"https://github.com/huggingface/transformers/tree/main/src/transformers/models/data2vec","n_code_links":12,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"MFAE","metrics":{"Accuracy":"90.54"},"uses_additional_data":false,"paper_date":"2020-05-07","paper":"/paper/what-do-questions-exactly-ask-mfae-duplicate","paper_url":"https://epubs.siam.org/doi/10.1137/1.9781611976236.26","paper_title":"What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis","code":"https://github.com/rzhangpku/MFAE","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"RE2","metrics":{"Accuracy":"89.2"},"uses_additional_data":false,"paper_date":"2019-08-01","paper":"/paper/simple-and-effective-text-matching-with-1","paper_url":"https://arxiv.org/abs/1908.00300v1","paper_title":"Simple and Effective Text Matching with Richer Alignment Features","code":"https://github.com/alibaba-edu/simple-effective-text-matching","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"MwAN","metrics":{"Accuracy":"89.12"},"uses_additional_data":false,"paper_date":"2018-07-01","paper":"/paper/multiway-attention-networks-for-modeling","paper_url":"https://www.ijcai.org/proceedings/2018/0613","paper_title":"Multiway Attention Networks for Modeling Sentence Pairs","code":"https://github.com/zsweet/zsw_AI_model","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DIIN","metrics":{"Accuracy":"89.06"},"uses_additional_data":false,"paper_date":"2017-09-13","paper":"/paper/natural-language-inference-over-interaction-1","paper_url":"http://arxiv.org/abs/1709.04348v2","paper_title":"Natural Language Inference over Interaction Space","code":"https://github.com/YichenGong/Densely-Interactive-Inference-Network","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"MSEM","metrics":{"Accuracy":"88.86"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/multi-task-sentence-encoding-model-for","paper_url":"https://arxiv.org/abs/1911.07405v1","paper_title":"Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"Bi-CAS-LSTM","metrics":{"Accuracy":"88.6"},"uses_additional_data":false,"paper_date":"2018-09-07","paper":"/paper/cell-aware-stacked-lstms-for-modeling","paper_url":"https://arxiv.org/abs/1809.02279v2","paper_title":"Cell-aware Stacked LSTMs for Modeling Sentences","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"pt-DecAtt","metrics":{"Accuracy":"88.40"},"uses_additional_data":false,"paper_date":"2017-04-15","paper":"/paper/neural-paraphrase-identification-of-questions","paper_url":"http://arxiv.org/abs/1704.04565v2","paper_title":"Neural Paraphrase Identification of Questions with Noisy Pretraining","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"TRANS-BLSTM","metrics":{"Accuracy":"88.28"},"uses_additional_data":false,"paper_date":"2020-03-16","paper":"/paper/trans-blstm-transformer-with-bidirectional","paper_url":"https://arxiv.org/abs/2003.07000v1","paper_title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"BiMPM","metrics":{"Accuracy":"88.17"},"uses_additional_data":false,"paper_date":"2017-02-13","paper":"/paper/bilateral-multi-perspective-matching-for","paper_url":"http://arxiv.org/abs/1702.03814v3","paper_title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","code":"https://github.com/google-research-datasets/paws","n_code_links":10,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"GenSen","metrics":{"Accuracy":"87.01"},"uses_additional_data":false,"paper_date":"2018-03-30","paper":"/paper/learning-general-purpose-distributed-sentence","paper_url":"http://arxiv.org/abs/1804.00079v1","paper_title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","code":"https://github.com/facebookresearch/InferSent","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":27,"model":"1-3[0.8pt/2pt] Random","metrics":{"Accuracy":"80"},"uses_additional_data":false,"paper_date":"2020-12-03","paper":"/paper/self-explaining-structures-improve-nlp-models","paper_url":"https://arxiv.org/abs/2012.01786v2","paper_title":"Self-Explaining Structures Improve NLP Models","code":"https://github.com/ShannonAI/Self_Explaining_Structures_Improve_NLP_Models","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"FreeLB","metrics":{"Accuracy":"74.8","Dev Accuracy":"92.6"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":29,"model":"BERT-Base","metrics":{"Direct Intrinsic Dimension":"9295","Structure Aware Intrinsic Dimension":"8030"},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/intrinsic-dimensionality-explains-the","paper_url":"https://arxiv.org/abs/2012.13255v1","paper_title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","code":"https://github.com/rabeehk/compacter","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":30,"model":"SMART-BERT","metrics":{"Dev Accuracy":"91.5","Dev F1":"88.5"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":31,"model":"SplitEE-S","metrics":{"Accuarcy":"71.1"},"uses_additional_data":false,"paper_date":"2023-09-17","paper":"/paper/splitee-early-exit-in-deep-neural-networks","paper_url":"https://arxiv.org/abs/2309.09195v1","paper_title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","code":"https://github.com/Div290/SplitEE/blob/main/README.md","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":18,"rows_with_any_sample_ran":17,"distinct_papers_with_graph_line":16,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":263,"n_unverified":494,"n_samples":757,"n_pointer_only_licence":170,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":279,"n_unverified":494,"n_samples":773,"n_pointer_only_licence":172,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}