{"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/paraphrase-identification","name":"Paraphrase Identification","slug":"paraphrase-identification","description_markdown":"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)","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":172,"papers_with_code":76,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"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":18,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/paraphrase-identification-on-quora-question","slug":"paraphrase-identification-on-quora-question","dataset":"Quora Question Pairs","dataset_url":"/dataset/quora-question-pairs","rows_in_archive":31,"metrics":["F1","Accuracy","Direct Intrinsic Dimension","Structure Aware Intrinsic Dimension","Dev Accuracy","Accuarcy","Dev F1"],"first_row_in_archive_order":{"model":"ALICE","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","paper_url":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_date":"2019-11-08","arxiv_id":"1911.03437","code_links":[{"title":"namisan/mt-dnn","url":"https://github.com/namisan/mt-dnn"},{"title":"microsoft/MT-DNN","url":"https://github.com/microsoft/MT-DNN"},{"title":"archinetai/smart-pytorch","url":"https://github.com/archinetai/smart-pytorch"},{"title":"archinetai/vat-pytorch","url":"https://github.com/archinetai/vat-pytorch"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"},{"title":"chunhuililili/mt_dnn","url":"https://github.com/chunhuililili/mt_dnn"}],"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smart-robust-and-efficient-fine-tuning-for#ran","syntology_url":"https://syntology.ai/paper/1911.03437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03437"}},"official":{"repos":["namisan/mt-dnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}},{"leaderboard":"/sota/paraphrase-identification-on-msrp","slug":"paraphrase-identification-on-msrp","dataset":"MSRP","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy","F1"],"first_row_in_archive_order":{"model":"FEAT2, TFKLD, SVM, Fine-grained features","paper_title":"Discriminative Improvements to Distributional Sentence Similarity","paper_url":"/paper/discriminative-improvements-to-distributional","paper_date":"2013-10-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/paraphrase-identification-on-quora-question-1","slug":"paraphrase-identification-on-quora-question-1","dataset":"Quora Question Pairs Dev","dataset_url":"/dataset/quora-question-pairs","rows_in_archive":2,"metrics":["Val Accuracy","Val F1 Score"],"first_row_in_archive_order":{"model":"BERT + SCH attm","paper_title":"Memory-efficient Stochastic methods for Memory-based Transformers","paper_url":"/paper/memory-efficient-stochastic-methods-for","paper_date":"2023-11-14","arxiv_id":"2311.08123","code_links":[{"title":"vishwajit-vishnu/memory-efficient-stochastic-methods-for-memory-based-transformers","url":"https://github.com/vishwajit-vishnu/memory-efficient-stochastic-methods-for-memory-based-transformers"}],"syntology":null}},{"leaderboard":"/sota/paraphrase-identification-on-2017-test-set","slug":"paraphrase-identification-on-2017-test-set","dataset":"2017_test set","dataset_url":null,"rows_in_archive":1,"metrics":["10 fold Cross validation"],"first_row_in_archive_order":{"model":"CNN","paper_title":"Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering","paper_url":"/paper/neural-network-models-for-paraphrase","paper_date":"2018-06-12","arxiv_id":"1806.04330","code_links":[{"title":"lanwuwei/SPM_toolkit","url":"https://github.com/lanwuwei/SPM_toolkit"}],"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-network-models-for-paraphrase#ran","syntology_url":"https://syntology.ai/paper/1806.04330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.04330"}},"official":{"repos":["lanwuwei/SPM_toolkit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/paraphrase-identification-on-ap","slug":"paraphrase-identification-on-ap","dataset":"AP","dataset_url":"/dataset/ap","rows_in_archive":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"RoBETRa base","paper_title":"Improving Paraphrase Detection with the Adversarial Paraphrasing Task","paper_url":"/paper/improving-paraphrase-detection-with-the","paper_date":"2021-06-14","arxiv_id":"2106.07691","code_links":[{"title":"Advancing-Machine-Human-Reasoning-Lab/apt","url":"https://github.com/Advancing-Machine-Human-Reasoning-Lab/apt"}],"syntology":null}},{"leaderboard":"/sota/paraphrase-identification-on-imdb","slug":"paraphrase-identification-on-imdb","dataset":"IMDb","dataset_url":"/dataset/imdb-movie-reviews","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SplitEE-S","paper_title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","paper_url":"/paper/splitee-early-exit-in-deep-neural-networks","paper_date":"2023-09-17","arxiv_id":"2309.09195","code_links":[{"title":"Div290/SplitEE","url":"https://github.com/Div290/SplitEE/blob/main/README.md"}],"syntology":null}},{"leaderboard":"/sota/paraphrase-identification-on-pit","slug":"paraphrase-identification-on-pit","dataset":"PIT","dataset_url":"/dataset/pit","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"TSDAE","paper_title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","paper_url":"/paper/tsdae-using-transformer-based-sequential","paper_date":"2021-04-14","arxiv_id":"2104.06979","code_links":[{"title":"kwang2049/pytorch-bertflow","url":"https://github.com/kwang2049/pytorch-bertflow"},{"title":"ukplab/pytorch-bertflow","url":"https://github.com/ukplab/pytorch-bertflow"},{"title":"kwang2049/useb","url":"https://github.com/kwang2049/useb"},{"title":"UKPLab/useb","url":"https://github.com/UKPLab/useb"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"exploration-lab/iitk-semeval-2024-task-1","url":"https://github.com/exploration-lab/iitk-semeval-2024-task-1"}],"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tsdae-using-transformer-based-sequential#ran","syntology_url":"https://syntology.ai/paper/2104.06979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06979"}},"official":{"repos":["kwang2049/pytorch-bertflow","kwang2049/useb","ukplab/pytorch-bertflow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/paraphrase-identification-on-translated-snli","slug":"paraphrase-identification-on-translated-snli","dataset":"Translated SNLI Dataset in Marathi","dataset_url":"/dataset/translated-snli-dataset-in-marathi","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Weighted Ensemble of TF-IDF and BERT Embeddings","paper_title":"Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing","paper_url":"/paper/enhancing-plagiarism-detection-in-marathi","paper_date":"2025-01-09","arxiv_id":"2501.05260","code_links":[{"title":"aditya-choudhary599/Marathi-Plagiarism-Detection","url":"https://github.com/aditya-choudhary599/Marathi-Plagiarism-Detection"}],"syntology":null}},{"leaderboard":"/sota/paraphrase-identification-on-turl","slug":"paraphrase-identification-on-turl","dataset":"TURL","dataset_url":"/dataset/twitter-news-url-corpus","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"TSDAE","paper_title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","paper_url":"/paper/tsdae-using-transformer-based-sequential","paper_date":"2021-04-14","arxiv_id":"2104.06979","code_links":[{"title":"kwang2049/pytorch-bertflow","url":"https://github.com/kwang2049/pytorch-bertflow"},{"title":"ukplab/pytorch-bertflow","url":"https://github.com/ukplab/pytorch-bertflow"},{"title":"kwang2049/useb","url":"https://github.com/kwang2049/useb"},{"title":"UKPLab/useb","url":"https://github.com/UKPLab/useb"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"exploration-lab/iitk-semeval-2024-task-1","url":"https://github.com/exploration-lab/iitk-semeval-2024-task-1"}],"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tsdae-using-transformer-based-sequential#ran","syntology_url":"https://syntology.ai/paper/2104.06979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06979"}},"official":{"repos":["kwang2049/pytorch-bertflow","kwang2049/useb","ukplab/pytorch-bertflow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/paraphrase-identification-on-wikihop","slug":"paraphrase-identification-on-wikihop","dataset":"WikiHop","dataset_url":"/dataset/wikihop","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"StructBERTRoBERTa ensemble","paper_title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","paper_url":"/paper/structbert-incorporating-language-structures","paper_date":"2019-08-13","arxiv_id":"1908.04577","code_links":[],"syntology":null}},{"leaderboard":"/sota/paraphrase-identification-on-yelp","slug":"paraphrase-identification-on-yelp","dataset":"Yelp","dataset_url":"/dataset/yelp","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SplitEE-S","paper_title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","paper_url":"/paper/splitee-early-exit-in-deep-neural-networks","paper_date":"2023-09-17","arxiv_id":"2309.09195","code_links":[{"title":"Div290/SplitEE","url":"https://github.com/Div290/SplitEE/blob/main/README.md"}],"syntology":null}}],"datasets":[{"url":"/dataset/imdb-movie-reviews","name":"IMDb Movie Reviews","full_name":"","num_papers_in_archive":1787},{"url":"/dataset/paws-x","name":"PAWS-X","full_name":"PAWS-X","num_papers_in_archive":172},{"url":"/dataset/paws","name":"PAWS","full_name":"Paraphrase Adversaries from Word Scrambling","num_papers_in_archive":159},{"url":"/dataset/yelp","name":"Yelp","full_name":"","num_papers_in_archive":86},{"url":"/dataset/wikihop","name":"WikiHop","full_name":"","num_papers_in_archive":66},{"url":"/dataset/quora-question-pairs","name":"Quora Question Pairs","full_name":"","num_papers_in_archive":55},{"url":"/dataset/pit","name":"PIT","full_name":"Paraphrase and Semantic Similarity in Twitter","num_papers_in_archive":22},{"url":"/dataset/paralex","name":"Paralex","full_name":"","num_papers_in_archive":20},{"url":"/dataset/flue-french-language-understanding-evaluation","name":"FLUE","full_name":"French Language Understanding Evaluation","num_papers_in_archive":12},{"url":"/dataset/twitter-news-url-corpus","name":"TURL","full_name":"Twitter News URL Corpus","num_papers_in_archive":6},{"url":"/dataset/finnish-paraphrase-corpus","name":"Finnish Paraphrase Corpus","full_name":"","num_papers_in_archive":4},{"url":"/dataset/sv-ident","name":"SV-Ident","full_name":"Survey Variable Identification","num_papers_in_archive":4},{"url":"/dataset/parade","name":"PARADE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/ap","name":"AP","full_name":"Adversarial Paraphrase","num_papers_in_archive":1},{"url":"/dataset/benchmark-for-neural-paraphrase-detection","name":"Autoencoder Paraphrase Dataset (AEPD)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/autoregressive-paraphrase-dataset-apd","name":"Autoregressive Paraphrase Dataset (ARPD)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/identifying-machine-paraphrased-plagiarism","name":"Machine Prarphrase Corpus (MPC)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/translated-snli-dataset-in-marathi","name":"Translated SNLI Dataset in Marathi","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity"}],"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":2,"rows_per_page":100,"shown":100,"of":172,"of_with_code":76,"tagged_in_all":172,"counts":{"archive_papers_tagged":172,"with_a_code_link":76,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":172,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","repositories_listed":534,"syntology":{"n":659,"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_honours":18,"n_violates":5,"n_no_contract":211,"n_pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}},"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","repositories_listed":27,"syntology":{"n":24,"n_ran":15,"n_constructed":2,"n_ran_checked":10,"n_instrument":5,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}},"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/data2vec-a-general-framework-for-self-1","slug":"data2vec-a-general-framework-for-self-1","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","date":"2022-02-07","arxiv_id":"2202.03555","repositories_listed":12,"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/data2vec-a-general-framework-for-self-1#ran","syntology_url":"https://syntology.ai/paper/2202.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03555"}},"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fnet-mixing-tokens-with-fourier-transforms","slug":"fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","repositories_listed":12,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fnet-mixing-tokens-with-fourier-transforms#ran","syntology_url":"https://syntology.ai/paper/2105.03824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03824"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","repositories_listed":10,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}},"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/bilateral-multi-perspective-matching-for","slug":"bilateral-multi-perspective-matching-for","title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","date":"2017-02-13","arxiv_id":"1702.03814","repositories_listed":10,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bilateral-multi-perspective-matching-for#ran","syntology_url":"https://syntology.ai/paper/1702.03814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.03814"}},"official":null}},{"url":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","repositories_listed":9,"syntology":{"n":17,"n_ran":8,"n_constructed":1,"n_ran_checked":1,"n_instrument":7,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/scaling-instruction-finetuned-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}},"official":null}},{"url":"/paper/abcnn-attention-based-convolutional-neural","slug":"abcnn-attention-based-convolutional-neural","title":"ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs","date":"2015-12-16","arxiv_id":"1512.05193","repositories_listed":8,"syntology":null},{"url":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","repositories_listed":7,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-task-deep-neural-networks-for-natural#ran","syntology_url":"https://syntology.ai/paper/1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}},"official":{"repos":["namisan/mt-dnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tsdae-using-transformer-based-sequential","slug":"tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","arxiv_id":"2104.06979","repositories_listed":6,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tsdae-using-transformer-based-sequential#ran","syntology_url":"https://syntology.ai/paper/2104.06979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06979"}},"official":{"repos":["kwang2049/pytorch-bertflow","kwang2049/useb","ukplab/pytorch-bertflow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/smart-robust-and-efficient-fine-tuning-for","slug":"smart-robust-and-efficient-fine-tuning-for","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","date":"2019-11-08","arxiv_id":"1911.03437","repositories_listed":6,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smart-robust-and-efficient-fine-tuning-for#ran","syntology_url":"https://syntology.ai/paper/1911.03437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03437"}},"official":{"repos":["namisan/mt-dnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","repositories_listed":6,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}},"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","repositories_listed":5,"syntology":null},{"url":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","slug":"dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dice-loss-for-data-imbalanced-nlp-tasks#ran","syntology_url":"https://syntology.ai/paper/1911.02855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02855"}},"official":{"repos":["ShannonAI/dice_loss_for_NLP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-general-purpose-distributed-sentence","slug":"learning-general-purpose-distributed-sentence","title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","date":"2018-03-30","arxiv_id":"1804.00079","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-general-purpose-distributed-sentence#ran","syntology_url":"https://syntology.ai/paper/1804.00079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00079"}},"official":{"repos":["facebookresearch/SentEval","Maluuba/gensen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entailment-as-few-shot-learner#ran","syntology_url":"https://syntology.ai/paper/2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"}},"official":null}},{"url":"/paper/paws-x-a-cross-lingual-adversarial-dataset","slug":"paws-x-a-cross-lingual-adversarial-dataset","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","date":"2019-08-30","arxiv_id":"1908.11828","repositories_listed":3,"syntology":null},{"url":"/paper/simple-and-effective-text-matching-with-1","slug":"simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-and-effective-text-matching-with-1#ran","syntology_url":"https://syntology.ai/paper/1908.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.00300"}},"official":{"repos":["hitvoice/RE2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-deep-relevance-matching-model-for-ad-hoc","slug":"a-deep-relevance-matching-model-for-ad-hoc","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","date":"2017-11-23","arxiv_id":"1711.08611","repositories_listed":3,"syntology":null},{"url":"/paper/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":3,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/charformer-fast-character-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2106.12672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12672"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/intrinsic-dimensionality-explains-the#ran","syntology_url":"https://syntology.ai/paper/2012.13255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.13255"}},"official":{"repos":["rabeehk/compacter"],"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/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","repositories_listed":2,"syntology":null},{"url":"/paper/adaptation-of-deep-bidirectional-multilingual","slug":"adaptation-of-deep-bidirectional-multilingual","title":"Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language","date":"2019-05-17","arxiv_id":"1905.07213","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-enhanced-language-representation-with","slug":"ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","arxiv_id":"1905.07129","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ernie-enhanced-language-representation-with#ran","syntology_url":"https://syntology.ai/paper/1905.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07129"}},"official":{"repos":["thunlp/ERNIE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/paws-paraphrase-adversaries-from-word","slug":"paws-paraphrase-adversaries-from-word","title":"PAWS: Paraphrase Adversaries from Word Scrambling","date":"2019-04-01","arxiv_id":"1904.01130","repositories_listed":2,"syntology":null},{"url":"/paper/natural-language-inference-over-interaction-1","slug":"natural-language-inference-over-interaction-1","title":"Natural Language Inference over Interaction Space","date":"2017-09-13","arxiv_id":"1709.04348","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/natural-language-inference-over-interaction-1#ran","syntology_url":"https://syntology.ai/paper/1709.04348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.04348"}},"official":{"repos":["YichenGong/Densely-Interactive-Inference-Network"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/enhancing-paraphrase-type-generation-the","slug":"enhancing-paraphrase-type-generation-the","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","date":"2025-05-28","arxiv_id":"2506.02018","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-plagiarism-detection-in-marathi","slug":"enhancing-plagiarism-detection-in-marathi","title":"Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing","date":"2025-01-09","arxiv_id":"2501.05260","repositories_listed":1,"syntology":null},{"url":"/paper/tougher-text-smarter-models-raising-the-bar","slug":"tougher-text-smarter-models-raising-the-bar","title":"Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks","date":"2025-01-05","arxiv_id":"2501.02654","repositories_listed":1,"syntology":null},{"url":"/paper/application-specific-compression-of-deep","slug":"application-specific-compression-of-deep","title":"Application Specific Compression of Deep Learning Models","date":"2024-09-09","arxiv_id":"2409.05368","repositories_listed":1,"syntology":null},{"url":"/paper/is-modularity-transferable-a-case-study","slug":"is-modularity-transferable-a-case-study","title":"Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation","date":"2024-03-27","arxiv_id":"2403.18804","repositories_listed":1,"syntology":null},{"url":"/paper/memory-efficient-stochastic-methods-for","slug":"memory-efficient-stochastic-methods-for","title":"Memory-efficient Stochastic methods for Memory-based Transformers","date":"2023-11-14","arxiv_id":"2311.08123","repositories_listed":1,"syntology":null},{"url":"/paper/splitee-early-exit-in-deep-neural-networks","slug":"splitee-early-exit-in-deep-neural-networks","title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","date":"2023-09-17","arxiv_id":"2309.09195","repositories_listed":1,"syntology":null},{"url":"/paper/do-multilingual-language-models-think-better","slug":"do-multilingual-language-models-think-better","title":"Do Multilingual Language Models Think Better in English?","date":"2023-08-02","arxiv_id":"2308.01223","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/do-multilingual-language-models-think-better#ran","syntology_url":"https://syntology.ai/paper/2308.01223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01223"}},"official":{"repos":["juletx/self-translate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/is-prompt-based-finetuning-always-better-than","slug":"is-prompt-based-finetuning-always-better-than","title":"Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding","date":"2023-07-15","arxiv_id":"2307.07880","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-word-importance-using-models","slug":"assessing-word-importance-using-models","title":"Assessing Word Importance Using Models Trained for Semantic Tasks","date":"2023-05-31","arxiv_id":"2305.19689","repositories_listed":1,"syntology":null},{"url":"/paper/cross-functional-analysis-of-generalisation","slug":"cross-functional-analysis-of-generalisation","title":"Cross-functional Analysis of Generalisation in Behavioural Learning","date":"2023-05-22","arxiv_id":"2305.12951","repositories_listed":1,"syntology":null},{"url":"/paper/co-driven-recognition-of-semantic-consistency","slug":"co-driven-recognition-of-semantic-consistency","title":"Co-Driven Recognition of Semantic Consistency via the Fusion of Transformer and HowNet Sememes Knowledge","date":"2023-02-21","arxiv_id":"2302.10570","repositories_listed":1,"syntology":null},{"url":"/paper/improving-word-mover-s-distance-by-leveraging","slug":"improving-word-mover-s-distance-by-leveraging","title":"Improving word mover's distance by leveraging self-attention matrix","date":"2022-11-11","arxiv_id":"2211.06229","repositories_listed":1,"syntology":null},{"url":"/paper/balanced-adversarial-training-balancing-1","slug":"balanced-adversarial-training-balancing-1","title":"Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models","date":"2022-10-20","arxiv_id":"2210.11498","repositories_listed":1,"syntology":null},{"url":"/paper/gapx-generalized-autoregressive-paraphrase","slug":"gapx-generalized-autoregressive-paraphrase","title":"GAPX: Generalized Autoregressive Paraphrase-Identification X","date":"2022-10-05","arxiv_id":"2210.01979","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/gapx-generalized-autoregressive-paraphrase#ran","syntology_url":"https://syntology.ai/paper/2210.01979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01979"}},"official":{"repos":["yifeizhou02/generalized_paraphrase_identification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-self-attention-for-language","slug":"adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","arxiv_id":"2206.12608","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-multilingual-sentence","slug":"evaluating-multilingual-sentence","title":"Evaluating Multilingual Sentence Representation Models in a Real Case Scenario","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rupaws-a-russian-adversarial-dataset-for","slug":"rupaws-a-russian-adversarial-dataset-for","title":"RuPAWS: A Russian Adversarial Dataset for Paraphrase Identification","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-better-characterization-of-1","slug":"towards-better-characterization-of-1","title":"Towards Better Characterization of Paraphrases","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nmtscore-a-multilingual-analysis-of","slug":"nmtscore-a-multilingual-analysis-of","title":"NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures","date":"2022-04-28","arxiv_id":"2204.13692","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multi-task-generalization-ability","slug":"improving-multi-task-generalization-ability","title":"Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning","date":"2022-04-06","arxiv_id":"2204.02725","repositories_listed":1,"syntology":null},{"url":"/paper/trans-encoder-unsupervised-sentence-pair","slug":"trans-encoder-unsupervised-sentence-pair","title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","date":"2021-09-27","arxiv_id":"2109.13059","repositories_listed":1,"syntology":null},{"url":"/paper/towards-better-characterization-of","slug":"towards-better-characterization-of","title":"Towards Better Characterization of Paraphrases","date":"2021-09-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modelling-latent-translations-for-cross","slug":"modelling-latent-translations-for-cross","title":"Modelling Latent Translations for Cross-Lingual Transfer","date":"2021-07-23","arxiv_id":"2107.11353","repositories_listed":1,"syntology":null},{"url":"/paper/improving-paraphrase-detection-with-the","slug":"improving-paraphrase-detection-with-the","title":"Improving Paraphrase Detection with the Adversarial Paraphrasing Task","date":"2021-06-14","arxiv_id":"2106.07691","repositories_listed":1,"syntology":null},{"url":"/paper/factorising-meaning-and-form-for-intent","slug":"factorising-meaning-and-form-for-intent","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","date":"2021-05-31","arxiv_id":"2105.15053","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-neural-network-predictions-on","slug":"explaining-neural-network-predictions-on","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","date":"2021-04-09","arxiv_id":"2104.04488","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/explaining-neural-network-predictions-on#ran","syntology_url":"https://syntology.ai/paper/2104.04488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04488"}},"official":{"repos":["UVa-NLP/GMASK"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-explaining-structures-improve-nlp-models","slug":"self-explaining-structures-improve-nlp-models","title":"Self-Explaining Structures Improve NLP Models","date":"2020-12-03","arxiv_id":"2012.01786","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-semantic-collisions","slug":"adversarial-semantic-collisions","title":"Adversarial Semantic Collisions","date":"2020-11-09","arxiv_id":"2011.04743","repositories_listed":1,"syntology":null},{"url":"/paper/parade-a-new-dataset-for-paraphrase","slug":"parade-a-new-dataset-for-paraphrase","title":"PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge","date":"2020-10-08","arxiv_id":"2010.03725","repositories_listed":1,"syntology":null},{"url":"/paper/bet-a-backtranslation-approach-for-easy-data","slug":"bet-a-backtranslation-approach-for-easy-data","title":"BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context","date":"2020-09-25","arxiv_id":"2009.12452","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-on-robustness-to-spurious","slug":"an-empirical-study-on-robustness-to-spurious","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","date":"2020-07-14","arxiv_id":"2007.06778","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-questions-exactly-ask-mfae-duplicate","slug":"what-do-questions-exactly-ask-mfae-duplicate","title":"What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis","date":"2020-05-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/191013291","slug":"191013291","title":"Sentence Embeddings for Russian NLU","date":"2019-10-29","arxiv_id":"1910.13291","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-fine-tuning-a-bert-case-study","slug":"transfer-fine-tuning-a-bert-case-study","title":"Transfer Fine-Tuning: A BERT Case Study","date":"2019-09-03","arxiv_id":"1909.00931","repositories_listed":1,"syntology":null},{"url":"/paper/training-complex-models-with-multi-task-weak","slug":"training-complex-models-with-multi-task-weak","title":"Training Complex Models with Multi-Task Weak Supervision","date":"2018-10-05","arxiv_id":"1810.02840","repositories_listed":1,"syntology":null},{"url":"/paper/paraphrase-thought-sentence-embedding-module","slug":"paraphrase-thought-sentence-embedding-module","title":"Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition","date":"2018-08-16","arxiv_id":"1808.05505","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-represent-bilingual-dictionaries","slug":"learning-to-represent-bilingual-dictionaries","title":"Learning to Represent Bilingual Dictionaries","date":"2018-08-10","arxiv_id":"1808.03726","repositories_listed":1,"syntology":null},{"url":"/paper/multiway-attention-networks-for-modeling","slug":"multiway-attention-networks-for-modeling","title":"Multiway Attention Networks for Modeling Sentence Pairs","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/to-attend-or-not-to-attend-a-case-study-on","slug":"to-attend-or-not-to-attend-a-case-study-on","title":"To Attend or not to Attend: A Case Study on Syntactic Structures for Semantic Relatedness","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-network-models-for-paraphrase","slug":"neural-network-models-for-paraphrase","title":"Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering","date":"2018-06-12","arxiv_id":"1806.04330","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-network-models-for-paraphrase#ran","syntology_url":"https://syntology.ai/paper/1806.04330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.04330"}},"official":{"repos":["lanwuwei/SPM_toolkit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/character-based-neural-networks-for-sentence","slug":"character-based-neural-networks-for-sentence","title":"Character-based Neural Networks for Sentence Pair Modeling","date":"2018-05-21","arxiv_id":"1805.08297","repositories_listed":1,"syntology":null},{"url":"/paper/etpc-a-paraphrase-identification-corpus","slug":"etpc-a-paraphrase-identification-corpus","title":"ETPC - A Paraphrase Identification Corpus Annotated with Extended Paraphrase Typology and Negation","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-neural-network-based-semantic","slug":"recurrent-neural-network-based-semantic","title":"Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning","date":"2018-02-09","arxiv_id":"1802.03238","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-non-trivial-paraphrase-corpus","slug":"building-a-non-trivial-paraphrase-corpus","title":"Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation Systems","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modelling-sentence-pairs-with-tree-structured","slug":"modelling-sentence-pairs-with-tree-structured","title":"Modelling Sentence Pairs with Tree-structured Attentive Encoder","date":"2016-10-10","arxiv_id":"1610.02806","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-matchpyramid-models-on-ad-hoc","slug":"a-study-of-matchpyramid-models-on-ad-hoc","title":"A Study of MatchPyramid Models on Ad-hoc Retrieval","date":"2016-06-15","arxiv_id":"1606.04648","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-similarity-learning-by-lexical","slug":"sentence-similarity-learning-by-lexical","title":"Sentence Similarity Learning by Lexical Decomposition and Composition","date":"2016-02-23","arxiv_id":"1602.07019","repositories_listed":1,"syntology":null},{"url":"/paper/idiom-paraphrases-seventh-heaven-vs-cloud","slug":"idiom-paraphrases-seventh-heaven-vs-cloud","title":"Idiom Paraphrases: Seventh Heaven vs Cloud Nine","date":"2015-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-neural-network-for-paraphrase","slug":"convolutional-neural-network-for-paraphrase","title":"Convolutional Neural Network for Paraphrase Identification","date":"2015-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"evaluating-the-effectiveness-of-linguistic","title":"Evaluating the Effectiveness of Linguistic Knowledge in Pretrained Language Models: A Case Study of Universal Dependencies","date":"2025-06-05","arxiv_id":"2506.04887","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-paraphrase-identification","title":"Cross-lingual paraphrase identification","date":"2024-06-21","arxiv_id":"2406.15066","repositories_listed":0,"syntology":null},{"url":null,"slug":"smoa-sparse-mixture-of-adapters-to-mitigate","title":"SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases","date":"2023-02-28","arxiv_id":"2302.14413","repositories_listed":0,"syntology":null},{"url":null,"slug":"paraphrase-identification-with-deep-learning","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","date":"2022-12-13","arxiv_id":"2212.06933","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-structure-aware-paraphrase","title":"Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders","date":"2022-10-11","arxiv_id":"2210.05302","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-large-scale-paraphrase-acquisition","title":"Improving Large-scale Paraphrase Acquisition and Generation","date":"2022-10-06","arxiv_id":"2210.03235","repositories_listed":0,"syntology":null},{"url":null,"slug":"paraphrasing-textual-entailment-and-semantic","title":"Paraphrasing, textual entailment, and semantic similarity above word level","date":"2022-08-10","arxiv_id":"2208.05387","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automatic-short-answer-assessment-for","title":"Towards Automatic Short Answer Assessment for Finnish as a Paraphrase Retrieval Task","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicate-argument-based-bi-encoder-for-1","title":"Predicate-Argument Based Bi-Encoder for Paraphrase Identification","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/perpada-a-persian-paraphrase-dataset-based-on","slug":"perpada-a-persian-paraphrase-dataset-based-on","title":"PerPaDa: A Persian Paraphrase Dataset based on Implicit Crowdsourcing Data Collection","date":"2022-01-17","arxiv_id":"2201.06573","repositories_listed":0,"syntology":null},{"url":null,"slug":"balanced-adversarial-training-balancing","title":"Balanced Adversarial Training: Balancing Tradeoffs Between Oversensitivity and Undersensitivity in NLP Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-prediction-uncertainty-of-pre","title":"Explaining Predictive Uncertainty by Looking Back at Model Explanations","date":"2022-01-11","arxiv_id":"2201.03742","repositories_listed":0,"syntology":null},{"url":null,"slug":"bnpc-a-corpus-for-paraphrase-detection-in","title":"BnPC: A Corpus for Paraphrase Detection in Bangla","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-shallow-and-deep-representations","title":"Combining Shallow and Deep Representations for Text-Pair Classification","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicate-argument-based-bi-encoder-for","title":"Predicate-Argument Based Bi-Encoder for Paraphrase Identification","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-guided-paraphrase-identification","title":"Knowledge-Guided Paraphrase Identification","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"task-adaptive-pre-training-and-self-training","title":"Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding","date":"2021-09-14","arxiv_id":"2109.06466","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-much-pretraining-data-do-language-models","title":"How much pretraining data do language models need to learn syntax?","date":"2021-09-07","arxiv_id":"2109.03160","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualized-embeddings-based-convolutional","title":"Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification","date":"2021-09-03","arxiv_id":"2109.01560","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-eligibility-of-backtranslated","title":"Assessing the Eligibility of Backtranslated Samples Based on Semantic Similarity for the Paraphrase Identification Task","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-bert-understand-idioms-a-probing-based","title":"Does BERT Understand Idioms? A Probing-Based Empirical Study of BERT Encodings of Idioms","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-domain-generalizable-paraphrase","title":"Towards Domain-Generalizable Paraphrase Identification by Avoiding the Shortcut Learning","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-yet-inconsistent-consistency","title":"Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models","date":"2021-08-15","arxiv_id":"2108.06665","repositories_listed":0,"syntology":null},{"url":null,"slug":"ladra-net-locally-aware-dynamic-re-read","title":"LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching","date":"2021-08-06","arxiv_id":"2108.02915","repositories_listed":0,"syntology":null}],"syntology_records":23,"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":22,"papers_where_code_ran_first_page":"/task/paraphrase-identification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/paraphrase-identification/papers/2","json":"/task/paraphrase-identification/papers/2.json","rows":72},{"order":"ran","page":1,"of":1,"url":"/task/paraphrase-identification/papers/ran/1","json":"/task/paraphrase-identification/papers/ran/1.json","rows":22}],"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":"0e9e4768c4d3966da68af4310b3fee31d7a23b593e278e20d7bec97f9d78af9e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}