{"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_with_a_benchmark_row":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","rows_on_this_dataset":5,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":10,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/memory-efficient-stochastic-methods-for","title":"Memory-efficient Stochastic methods for Memory-based Transformers","date":"2023-11-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/splitee-early-exit-in-deep-neural-networks","title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","date":"2023-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-sketch-induction-for-paraphrase","title":"Hierarchical Sketch Induction for Paraphrase Generation","date":"2022-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/factorising-meaning-and-form-for-intent","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","date":"2021-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/clear-contrastive-learning-for-sentence","title":"CLEAR: Contrastive Learning for Sentence Representation","date":"2020-12-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/self-explaining-structures-improve-nlp-models","title":"Self-Explaining Structures Improve NLP Models","date":"2020-12-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":10,"samples_unverified":5,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":4,"samples_unverified":9,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":40,"samples_ran":26,"samples_unverified":14,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/trans-blstm-transformer-with-bidirectional","title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","date":"2020-03-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-sentence-encoding-model-for","title":"Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems","date":"2019-11-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","rows_on_this_dataset":5,"code_links":57,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":2,"samples_unverified":29,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":27,"samples_ran":19,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":126,"samples_ran":46,"samples_unverified":80,"pointer_only_for_licence":22,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":48,"samples_ran":22,"samples_unverified":26,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":10,"samples_unverified":14,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":5,"samples_unverified":8,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","date":"2018-12-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","rows_on_this_dataset":1,"code_links":534,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":659,"samples_ran":204,"samples_unverified":455,"pointer_only_for_licence":149,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/training-complex-models-with-multi-task-weak","title":"Training Complex Models with Multi-Task Weak Supervision","date":"2018-10-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cell-aware-stacked-lstms-for-modeling","title":"Cell-aware Stacked LSTMs for Modeling Sentences","date":"2018-09-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multiway-attention-networks-for-modeling","title":"Multiway Attention Networks for Modeling Sentence Pairs","date":"2018-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-general-purpose-distributed-sentence","title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","date":"2018-03-30","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/natural-language-inference-over-interaction-1","title":"Natural Language Inference over Interaction Space","date":"2017-09-13","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-paraphrase-identification-of-questions","title":"Neural Paraphrase Identification of Questions with Noisy Pretraining","date":"2017-04-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bilateral-multi-perspective-matching-for","title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","date":"2017-02-13","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":27,"samples_harvested":1084,"samples_ran":390,"samples_unverified":694,"pointer_only_for_licence":240,"papers_with_no_sample_that_ran":4,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}