{"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/quora-question-pairs","name":"Quora Question Pairs","full_name":null,"description_markdown":"**Quora Question Pairs** (QQP) dataset consists of over 400,000 question pairs, and each question pair is annotated with a binary value indicating whether the two questions are paraphrase of each other.\r\n\r\nSource: [Bilateral Multi-Perspective Matching for Natural Language Sentences](/paper/bilateral-multi-perspective-matching-for)","description_withheld":null,"homepage":"https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Custom (non-commercial)","url":"https://www.quora.com/about/tos"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"},{"name":"Paraphrase Generation","url":"/task/paraphrase-generation","datasets_with_task":"/datasets/task/paraphrase-generation"},{"name":"Community Question Answering","url":"/task/community-question-answering","datasets_with_task":"/datasets/task/community-question-answering"},{"name":"Paraphrase Identification within Bi-Encoder","url":"/task/paraphrase-identification-within-bi-encoder","datasets_with_task":"/datasets/task/paraphrase-identification-within-bi-encoder"},{"name":"QQP","url":"/task/qqp","datasets_with_task":"/datasets/task/qqp"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Quora Question Pairs","Quora Question Pairs Dev","qqp"],"data_loaders":[{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/pair_classification/dataset_readers/quora_paraphrase/","frameworks":["pytorch"]}],"num_papers_in_archive":55,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/paraphrase-identification-on-quora-question","task":"Paraphrase Identification","dataset_variant":"Quora Question Pairs","rows":31,"metrics":["F1","Accuracy","Direct Intrinsic Dimension","Structure Aware Intrinsic Dimension","Dev Accuracy","Accuarcy","Dev F1"],"first_row_in_archive_order":{"model":"ALICE","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","metrics":{"F1":"90.7"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-quora-question-pairs","task":"Question Answering","dataset_variant":"Quora Question Pairs","rows":19,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLNet (single model)","paper":"/paper/xlnet-generalized-autoregressive-pretraining","metrics":{"Accuracy":"92.3%"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/retrieval-on-quora-question-pairs","task":"Retrieval","dataset_variant":"Quora Question Pairs","rows":4,"metrics":["Queries per second"],"first_row_in_archive_order":{"model":"BM25S","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","metrics":{"Queries per second":"183.53"},"code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/paraphrase-generation-on-quora-question-pairs-1","task":"Paraphrase Generation","dataset_variant":"Quora Question Pairs","rows":2,"metrics":["iBLEU","BLEU"],"first_row_in_archive_order":{"model":"HRQ-VAE","paper":"/paper/hierarchical-sketch-induction-for-paraphrase","metrics":{"BLEU":"33.11","iBLEU":"18.42"},"code_links":[{"title":"tomhosking/hrq-vae","url":"https://github.com/tomhosking/hrq-vae"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/paraphrase-identification-on-quora-question-1","task":"Paraphrase Identification","dataset_variant":"Quora Question Pairs Dev","rows":2,"metrics":["Val Accuracy","Val F1 Score"],"first_row_in_archive_order":{"model":"BERT + SCH attm","paper":"/paper/memory-efficient-stochastic-methods-for","metrics":{"Val Accuracy":"91.422"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/community-question-answering-on-quora","task":"Community Question Answering","dataset_variant":"Quora Question Pairs","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MFAE","paper":"/paper/what-do-questions-exactly-ask-mfae-duplicate","metrics":{"Accuracy":"90.54"},"code_links":[{"title":"rzhangpku/MFAE","url":"https://github.com/rzhangpku/MFAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-quora-question","task":"Natural Language Inference","dataset_variant":"Quora Question Pairs","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"aESIM","paper":"/paper/attention-boosted-sequential-inference-model","metrics":{"Accuracy":"88.01"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-retrieval-on-quora-question-pairs","task":"Text Retrieval","dataset_variant":"Quora Question Pairs","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","metrics":{"nDCG@10":"78.7"},"code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}]},"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":45,"of":45,"counts":{"papers_with_a_benchmark_row":45,"with_a_code_link":38,"where_syntology_ran_a_sample":25,"not_listed_spam_title":0,"listed":45,"listed_where_code_ran":25,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":22,"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 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/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","rows_on_this_dataset":5,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-sketch-induction-for-paraphrase","slug":"hierarchical-sketch-induction-for-paraphrase","title":"Hierarchical Sketch Induction for Paraphrase Generation","date":"2022-03-07","arxiv_id":"2203.03463","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["tomhosking/hrq-vae"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hierarchical-sketch-induction-for-paraphrase#ran","syntology_url":"https://syntology.ai/paper/2203.03463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03463"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":12,"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":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/clear-contrastive-learning-for-sentence","slug":"clear-contrastive-learning-for-sentence","title":"CLEAR: Contrastive Learning for Sentence Representation","date":"2020-12-31","arxiv_id":"2012.15466","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"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/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","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":["huggingface/transformers"],"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/squeezebert-what-can-computer-vision-teach#ran","syntology_url":"https://syntology.ai/paper/2006.11316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11316"}}}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/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,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":31,"samples_constructed":7,"samples_ran_checked":18,"samples_ran_instrument_failed":13,"samples_unverified":9,"pointer_only_for_licence":10,"official":{"repos":["google-research/electra"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/electra-pre-training-text-encoders-as-1#ran","syntology_url":"https://syntology.ai/paper/2003.10555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10555"}}}},{"paper":"/paper/trans-blstm-transformer-with-bidirectional","slug":"trans-blstm-transformer-with-bidirectional","title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","date":"2020-03-16","arxiv_id":"2003.07000","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-sentence-encoding-model-for","slug":"multi-task-sentence-encoding-model-for","title":"Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems","date":"2019-11-18","arxiv_id":"1911.07405","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":5,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":21,"samples_constructed":5,"samples_ran_checked":12,"samples_ran_instrument_failed":9,"samples_unverified":6,"pointer_only_for_licence":2,"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":56,"samples_ran_instrument_failed":25,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"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":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}}}},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"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":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"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/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/attention-boosted-sequential-inference-model","slug":"attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","date":"2018-12-05","arxiv_id":"1812.01840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cell-aware-stacked-lstms-for-modeling","slug":"cell-aware-stacked-lstms-for-modeling","title":"Cell-aware Stacked LSTMs for Modeling Sentences","date":"2018-09-07","arxiv_id":"1809.02279","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","slug":"baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","arxiv_id":"1805.09843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","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":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/neural-paraphrase-identification-of-questions","slug":"neural-paraphrase-identification-of-questions","title":"Neural Paraphrase Identification of Questions with Noisy Pretraining","date":"2017-04-15","arxiv_id":"1704.04565","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","rows_on_this_dataset":5,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-sketch-induction-for-paraphrase","slug":"hierarchical-sketch-induction-for-paraphrase","title":"Hierarchical Sketch Induction for Paraphrase Generation","date":"2022-03-07","arxiv_id":"2203.03463","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["tomhosking/hrq-vae"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hierarchical-sketch-induction-for-paraphrase#ran","syntology_url":"https://syntology.ai/paper/2203.03463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03463"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":12,"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":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/clear-contrastive-learning-for-sentence","slug":"clear-contrastive-learning-for-sentence","title":"CLEAR: Contrastive Learning for Sentence Representation","date":"2020-12-31","arxiv_id":"2012.15466","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"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/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","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":["huggingface/transformers"],"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/squeezebert-what-can-computer-vision-teach#ran","syntology_url":"https://syntology.ai/paper/2006.11316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11316"}}}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/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,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":31,"samples_constructed":7,"samples_ran_checked":18,"samples_ran_instrument_failed":13,"samples_unverified":9,"pointer_only_for_licence":10,"official":{"repos":["google-research/electra"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/electra-pre-training-text-encoders-as-1#ran","syntology_url":"https://syntology.ai/paper/2003.10555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10555"}}}},{"paper":"/paper/trans-blstm-transformer-with-bidirectional","slug":"trans-blstm-transformer-with-bidirectional","title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","date":"2020-03-16","arxiv_id":"2003.07000","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-sentence-encoding-model-for","slug":"multi-task-sentence-encoding-model-for","title":"Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems","date":"2019-11-18","arxiv_id":"1911.07405","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":5,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":21,"samples_constructed":5,"samples_ran_checked":12,"samples_ran_instrument_failed":9,"samples_unverified":6,"pointer_only_for_licence":2,"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":56,"samples_ran_instrument_failed":25,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"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":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190910351#ran","syntology_url":"https://syntology.ai/paper/1909.10351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10351"}}}},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"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":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"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/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/attention-boosted-sequential-inference-model","slug":"attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","date":"2018-12-05","arxiv_id":"1812.01840","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":659,"samples_ran":300,"samples_constructed":75,"samples_ran_checked":234,"samples_ran_instrument_failed":66,"samples_unverified":359,"pointer_only_for_licence":164,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cell-aware-stacked-lstms-for-modeling","slug":"cell-aware-stacked-lstms-for-modeling","title":"Cell-aware Stacked LSTMs for Modeling Sentences","date":"2018-09-07","arxiv_id":"1809.02279","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","slug":"baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","arxiv_id":"1805.09843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","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":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/neural-paraphrase-identification-of-questions","slug":"neural-paraphrase-identification-of-questions","title":"Neural Paraphrase Identification of Questions with Noisy Pretraining","date":"2017-04-15","arxiv_id":"1704.04565","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"papers_where_code_ran":25,"papers_where_code_ran_first_page":"/dataset/quora-question-pairs/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/quora-question-pairs/papers/ran/1","json":"/dataset/quora-question-pairs/papers/ran/1.json","rows":25}],"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":27,"samples_harvested":1084,"samples_ran":589,"samples_constructed":122,"samples_ran_checked":434,"samples_ran_instrument_failed":155,"samples_unverified":495,"pointer_only_for_licence":270,"papers_with_no_sample_that_ran":2,"papers_with_a_sample_that_ran":25,"papers_with_a_run_with_no_instrument_failure":22,"papers_where_every_run_was_an_instrument_failure":3,"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/question-answering-on-quora-question-pairs","since_archive":"/sota/question-answering-on-quora-question-pairs#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":"455e33237845a45ce02aaedd929cd0eb25fb33114956f3c07e7763a95b062ec3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}