{"url":"/sota/machine-translation-on-wmt2014-english-french","task":{"name":"Machine Translation","url":"/task/machine-translation","note":null},"dataset":{"name":"WMT2014 English-French","url":"/dataset/wmt-2014"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Machine translation** is the task of translating a sentence in a source language to a different target language.\r\n\r\nApproaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation. \r\n\r\nOne of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others. \r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Google seq2seq](https://github.com/google/seq2seq) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["BLEU score","SacreBLEU","Hardware Burden","Operations per network pass"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BLEU score":"higher","SacreBLEU":null,"Hardware Burden":null,"Operations per network pass":null}},"counts":{"rows":57,"rows_with_code":54,"rows_with_paper_page":56,"rows_dated":56,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"Transformer+BT (ADMIN init)","metrics":{"BLEU score":"46.4","SacreBLEU":"44.4"},"uses_additional_data":true,"paper_date":"2020-08-18","paper":"/paper/very-deep-transformers-for-neural-machine","paper_url":"https://arxiv.org/abs/2008.07772v2","paper_title":"Very Deep Transformers for Neural Machine Translation","code":"https://github.com/LiyuanLucasLiu/Transforemr-Clinic","n_code_links":4,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Noisy back-translation","metrics":{"BLEU score":"45.6","Hardware Burden":"180G","SacreBLEU":"43.8"},"uses_additional_data":true,"paper_date":"2018-08-28","paper":"/paper/understanding-back-translation-at-scale","paper_url":"http://arxiv.org/abs/1808.09381v2","paper_title":"Understanding Back-Translation at Scale","code":"https://github.com/facebookresearch/fairseq","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"mRASP+Fine-Tune","metrics":{"BLEU score":"44.3","SacreBLEU":"41.7"},"uses_additional_data":true,"paper_date":"2020-10-07","paper":"/paper/pre-training-multilingual-neural-machine","paper_url":"https://arxiv.org/abs/2010.03142v3","paper_title":"Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information","code":"https://github.com/linzehui/mRASP","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Transformer + R-Drop","metrics":{"BLEU score":"43.95"},"uses_additional_data":false,"paper_date":"2021-06-28","paper":"/paper/r-drop-regularized-dropout-for-neural","paper_url":"https://arxiv.org/abs/2106.14448v2","paper_title":"R-Drop: Regularized Dropout for Neural Networks","code":"https://github.com/dropreg/R-Drop","n_code_links":8,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Transformer (ADMIN init)","metrics":{"BLEU score":"43.8","SacreBLEU":"41.8"},"uses_additional_data":false,"paper_date":"2020-08-18","paper":"/paper/very-deep-transformers-for-neural-machine","paper_url":"https://arxiv.org/abs/2008.07772v2","paper_title":"Very Deep Transformers for Neural Machine Translation","code":"https://github.com/LiyuanLucasLiu/Transforemr-Clinic","n_code_links":4,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Admin","metrics":{"BLEU score":"43.8"},"uses_additional_data":false,"paper_date":"2020-04-17","paper":"/paper/understanding-the-difficulty-of-training","paper_url":"https://arxiv.org/abs/2004.08249v3","paper_title":"Understanding the Difficulty of Training Transformers","code":"https://github.com/LiyuanLucasLiu/Transforemr-Clinic","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"BERT-fused NMT","metrics":{"BLEU score":"43.78"},"uses_additional_data":true,"paper_date":"2020-02-17","paper":"/paper/incorporating-bert-into-neural-machine-1","paper_url":"https://arxiv.org/abs/2002.06823v1","paper_title":"Incorporating BERT into Neural Machine Translation","code":"https://github.com/bert-nmt/bert-nmt","n_code_links":3,"syntology":null},{"rank_in_archive_order":8,"model":"MUSE(Paralllel Multi-scale Attention)","metrics":{"BLEU score":"43.5"},"uses_additional_data":false,"paper_date":"2019-11-17","paper":"/paper/muse-parallel-multi-scale-attention-for","paper_url":"https://arxiv.org/abs/1911.09483v1","paper_title":"MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning","code":"https://github.com/lancopku/MUSE","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"T5","metrics":{"BLEU score":"43.4"},"uses_additional_data":true,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"Local Joint Self-attention","metrics":{"BLEU score":"43.3"},"uses_additional_data":false,"paper_date":"2019-05-16","paper":"/paper/190506596","paper_url":"https://arxiv.org/abs/1905.06596v1","paper_title":"Joint Source-Target Self Attention with Locality Constraints","code":"https://github.com/jarfo/joint","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"Depth Growing","metrics":{"BLEU score":"43.27","Hardware Burden":"24G"},"uses_additional_data":false,"paper_date":"2019-07-03","paper":"/paper/depth-growing-for-neural-machine-translation","paper_url":"https://arxiv.org/abs/1907.01968v1","paper_title":"Depth Growing for Neural Machine Translation","code":"https://github.com/apeterswu/Depth_Growing_NMT","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Transformer Big","metrics":{"BLEU score":"43.2","Hardware Burden":"55G"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/scaling-neural-machine-translation","paper_url":"http://arxiv.org/abs/1806.00187v3","paper_title":"Scaling Neural Machine Translation","code":"https://github.com/facebookresearch/fairseq","n_code_links":5,"syntology":null},{"rank_in_archive_order":13,"model":"DynamicConv","metrics":{"BLEU score":"43.2"},"uses_additional_data":false,"paper_date":"2019-01-29","paper":"/paper/pay-less-attention-with-lightweight-and","paper_url":"http://arxiv.org/abs/1901.10430v2","paper_title":"Pay Less Attention with Lightweight and Dynamic Convolutions","code":"https://github.com/pytorch/fairseq","n_code_links":3,"syntology":null},{"rank_in_archive_order":14,"model":"TaLK Convolutions","metrics":{"BLEU score":"43.2"},"uses_additional_data":false,"paper_date":"2020-02-08","paper":"/paper/time-aware-large-kernel-convolutions","paper_url":"https://arxiv.org/abs/2002.03184v2","paper_title":"Time-aware Large Kernel Convolutions","code":"https://github.com/lioutasb/TaLKConvolutions","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"LightConv","metrics":{"BLEU score":"43.1"},"uses_additional_data":false,"paper_date":"2019-01-29","paper":"/paper/pay-less-attention-with-lightweight-and","paper_url":"http://arxiv.org/abs/1901.10430v2","paper_title":"Pay Less Attention with Lightweight and Dynamic Convolutions","code":"https://github.com/pytorch/fairseq","n_code_links":3,"syntology":null},{"rank_in_archive_order":16,"model":"FLOATER-large","metrics":{"BLEU score":"42.7"},"uses_additional_data":false,"paper_date":"2020-03-13","paper":"/paper/learning-to-encode-position-for-transformer","paper_url":"https://arxiv.org/abs/2003.09229v1","paper_title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","code":"https://github.com/xuanqing94/FLOATER","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":17,"model":"OmniNetP","metrics":{"BLEU score":"42.6"},"uses_additional_data":false,"paper_date":"2021-03-01","paper":"/paper/omninet-omnidirectional-representations-from","paper_url":"https://arxiv.org/abs/2103.01075v1","paper_title":"OmniNet: Omnidirectional Representations from Transformers","code":"https://github.com/lucidrains/omninet-pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"Transformer Big + MoS","metrics":{"BLEU score":"42.1"},"uses_additional_data":false,"paper_date":"2018-09-25","paper":"/paper/fast-and-simple-mixture-of-softmaxes-with-bpe","paper_url":"https://arxiv.org/abs/1809.09296v2","paper_title":"Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation","code":"https://github.com/shawnkx/Fast-MoS","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"T2R + Pretrain","metrics":{"BLEU score":"42.1"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/finetuning-pretrained-transformers-into-rnns","paper_url":"https://arxiv.org/abs/2103.13076v2","paper_title":"Finetuning Pretrained Transformers into RNNs","code":"https://github.com/hazyresearch/lolcats","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":4}},{"rank_in_archive_order":20,"model":"Synthesizer (Random + Vanilla)","metrics":{"BLEU score":"41.85"},"uses_additional_data":false,"paper_date":"2020-05-02","paper":"/paper/synthesizer-rethinking-self-attention-in","paper_url":"https://arxiv.org/abs/2005.00743v3","paper_title":"Synthesizer: Rethinking Self-Attention in Transformer Models","code":"https://github.com/10-zin/Synthesizer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"Hardware Aware Transformer","metrics":{"BLEU score":"41.8"},"uses_additional_data":false,"paper_date":"2020-05-28","paper":"/paper/hat-hardware-aware-transformers-for-efficient","paper_url":"https://arxiv.org/abs/2005.14187v1","paper_title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","code":"https://github.com/mit-han-lab/hardware-aware-transformers","n_code_links":4,"syntology":null},{"rank_in_archive_order":22,"model":"Transformer (big) + Relative Position Representations","metrics":{"BLEU score":"41.5"},"uses_additional_data":false,"paper_date":"2018-03-06","paper":"/paper/self-attention-with-relative-position","paper_url":"http://arxiv.org/abs/1803.02155v2","paper_title":"Self-Attention with Relative Position Representations","code":"https://github.com/tensorflow/tensor2tensor","n_code_links":13,"syntology":{"n_ran":13,"n_unverified":10,"n_samples":23,"n_pointer_only_licence":3}},{"rank_in_archive_order":23,"model":"Stack 4-layer RNNSearch + Dual Learning + Deliberation Network","metrics":{"BLEU score":"41.5"},"uses_additional_data":false,"paper_date":"2017-12-01","paper":"/paper/deliberation-networks-sequence-generation","paper_url":"http://papers.nips.cc/paper/6775-deliberation-networks-sequence-generation-beyond-one-pass-decoding","paper_title":"Deliberation Networks: Sequence Generation Beyond One-Pass Decoding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"Weighted Transformer (large)","metrics":{"BLEU score":"41.4"},"uses_additional_data":false,"paper_date":"2017-11-06","paper":"/paper/weighted-transformer-network-for-machine","paper_url":"http://arxiv.org/abs/1711.02132v1","paper_title":"Weighted Transformer Network for Machine Translation","code":"https://github.com/JayParks/transformer","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":25,"model":"ConvS2S (ensemble)","metrics":{"BLEU score":"41.3"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/convolutional-sequence-to-sequence-learning","paper_url":"http://arxiv.org/abs/1705.03122v3","paper_title":"Convolutional Sequence to Sequence Learning","code":"https://github.com/facebookresearch/fairseq","n_code_links":37,"syntology":null},{"rank_in_archive_order":26,"model":"Evolved Transformer Big","metrics":{"BLEU score":"41.3"},"uses_additional_data":false,"paper_date":"2019-01-30","paper":"/paper/the-evolved-transformer","paper_url":"https://arxiv.org/abs/1901.11117v4","paper_title":"The Evolved Transformer","code":"https://github.com/tensorflow/tensor2tensor","n_code_links":3,"syntology":null},{"rank_in_archive_order":27,"model":"RNMT+","metrics":{"BLEU score":"41.0","Hardware Burden":"132G","Operations per network pass":"2.81G"},"uses_additional_data":false,"paper_date":"2018-04-26","paper":"/paper/the-best-of-both-worlds-combining-recent","paper_url":"http://arxiv.org/abs/1804.09849v2","paper_title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","code":"https://github.com/tensorflow/lingvo","n_code_links":3,"syntology":null},{"rank_in_archive_order":28,"model":"Transformer Big","metrics":{"BLEU score":"41.0","Hardware Burden":"23G","Operations per network pass":"2300000000.0G"},"uses_additional_data":true,"paper_date":"2017-06-12","paper":"/paper/attention-is-all-you-need","paper_url":"https://arxiv.org/abs/1706.03762v7","paper_title":"Attention Is All You Need","code":"https://github.com/huggingface/transformers","n_code_links":595,"syntology":{"n_ran":610,"n_unverified":336,"n_samples":946,"n_pointer_only_licence":451}},{"rank_in_archive_order":29,"model":"Evolved Transformer Base","metrics":{"BLEU score":"40.6"},"uses_additional_data":false,"paper_date":"2019-01-30","paper":"/paper/the-evolved-transformer","paper_url":"https://arxiv.org/abs/1901.11117v4","paper_title":"The Evolved Transformer","code":"https://github.com/tensorflow/tensor2tensor","n_code_links":3,"syntology":null},{"rank_in_archive_order":30,"model":"ResMLP-12","metrics":{"BLEU score":"40.6"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"MoE","metrics":{"BLEU score":"40.56","Hardware Burden":"142G"},"uses_additional_data":false,"paper_date":"2017-01-23","paper":"/paper/outrageously-large-neural-networks-the","paper_url":"http://arxiv.org/abs/1701.06538v1","paper_title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","code":"https://github.com/davidmrau/mixture-of-experts","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":32,"model":"Transformer","metrics":{"BLEU score":"40.5"},"uses_additional_data":false,"paper_date":"2019-01-30","paper":"/paper/memory-efficient-adaptive-optimization-for","paper_url":"https://arxiv.org/abs/1901.11150v2","paper_title":"Memory-Efficient Adaptive Optimization","code":"https://github.com/google-research/google-research/tree/master/sm3","n_code_links":4,"syntology":null},{"rank_in_archive_order":33,"model":"ConvS2S","metrics":{"BLEU score":"40.46","Hardware Burden":"143G"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/convolutional-sequence-to-sequence-learning","paper_url":"http://arxiv.org/abs/1705.03122v3","paper_title":"Convolutional Sequence to Sequence Learning","code":"https://github.com/facebookresearch/fairseq","n_code_links":37,"syntology":null},{"rank_in_archive_order":34,"model":"ResMLP-6","metrics":{"BLEU score":"40.3"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"TransformerBase + AutoDropout","metrics":{"BLEU score":"40"},"uses_additional_data":false,"paper_date":"2021-01-05","paper":"/paper/autodropout-learning-dropout-patterns-to","paper_url":"https://arxiv.org/abs/2101.01761v1","paper_title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","code":"https://github.com/google-research/google-research","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"GNMT+RL","metrics":{"BLEU score":"39.9","Hardware Burden":"279G"},"uses_additional_data":false,"paper_date":"2016-09-26","paper":"/paper/googles-neural-machine-translation-system","paper_url":"http://arxiv.org/abs/1609.08144v2","paper_title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","code":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Translation/GNMT","n_code_links":28,"syntology":{"n_ran":23,"n_unverified":23,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":37,"model":"Lite Transformer","metrics":{"BLEU score":"39.6"},"uses_additional_data":false,"paper_date":"2020-04-24","paper":"/paper/lite-transformer-with-long-short-range","paper_url":"https://arxiv.org/abs/2004.11886v1","paper_title":"Lite Transformer with Long-Short Range Attention","code":"https://github.com/mit-han-lab/lite-transformer","n_code_links":2,"syntology":null},{"rank_in_archive_order":38,"model":"Deep-Att + PosUnk","metrics":{"BLEU score":"39.2","Hardware Burden":"119G"},"uses_additional_data":false,"paper_date":"2016-06-14","paper":"/paper/deep-recurrent-models-with-fast-forward","paper_url":"http://arxiv.org/abs/1606.04199v3","paper_title":"Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation","code":"https://github.com/fstahlberg/tensor2tensor-usr","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"Rfa-Gate-arccos","metrics":{"BLEU score":"39.2"},"uses_additional_data":false,"paper_date":"2021-03-03","paper":"/paper/random-feature-attention-1","paper_url":"https://arxiv.org/abs/2103.02143v2","paper_title":"Random Feature Attention","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"Transformer Base","metrics":{"BLEU score":"38.1","Hardware Burden":"23G","Operations per network pass":"330000000.0G"},"uses_additional_data":false,"paper_date":"2017-06-12","paper":"/paper/attention-is-all-you-need","paper_url":"https://arxiv.org/abs/1706.03762v7","paper_title":"Attention Is All You Need","code":"https://github.com/huggingface/transformers","n_code_links":595,"syntology":{"n_ran":610,"n_unverified":336,"n_samples":946,"n_pointer_only_licence":451}},{"rank_in_archive_order":41,"model":"LSTM6 + PosUnk","metrics":{"BLEU score":"37.5"},"uses_additional_data":false,"paper_date":"2014-10-30","paper":"/paper/addressing-the-rare-word-problem-in-neural","paper_url":"http://arxiv.org/abs/1410.8206v4","paper_title":"Addressing the Rare Word Problem in Neural Machine Translation","code":"https://github.com/atpaino/deep-text-corrector","n_code_links":5,"syntology":null},{"rank_in_archive_order":42,"model":"PBMT","metrics":{"BLEU score":"37"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"SMT+LSTM5","metrics":{"BLEU score":"36.5"},"uses_additional_data":false,"paper_date":"2014-09-10","paper":"/paper/sequence-to-sequence-learning-with-neural","paper_url":"http://arxiv.org/abs/1409.3215v3","paper_title":"Sequence to Sequence Learning with Neural Networks","code":"https://github.com/bentrevett/pytorch-seq2seq","n_code_links":74,"syntology":{"n_ran":14,"n_unverified":11,"n_samples":25,"n_pointer_only_licence":9}},{"rank_in_archive_order":44,"model":"RNN-search50*","metrics":{"BLEU score":"36.2"},"uses_additional_data":false,"paper_date":"2014-09-01","paper":"/paper/neural-machine-translation-by-jointly","paper_url":"http://arxiv.org/abs/1409.0473v7","paper_title":"Neural Machine Translation by Jointly Learning to Align and Translate","code":"https://github.com/graykode/nlp-tutorial","n_code_links":124,"syntology":{"n_ran":21,"n_unverified":23,"n_samples":44,"n_pointer_only_licence":16}},{"rank_in_archive_order":45,"model":"Deep-Att","metrics":{"BLEU score":"35.9"},"uses_additional_data":false,"paper_date":"2016-06-14","paper":"/paper/deep-recurrent-models-with-fast-forward","paper_url":"http://arxiv.org/abs/1606.04199v3","paper_title":"Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation","code":"https://github.com/fstahlberg/tensor2tensor-usr","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"Deep Convolutional Encoder; single-layer decoder","metrics":{"BLEU score":"35.7"},"uses_additional_data":false,"paper_date":"2016-11-07","paper":"/paper/a-convolutional-encoder-model-for-neural","paper_url":"http://arxiv.org/abs/1611.02344v3","paper_title":"A Convolutional Encoder Model for Neural Machine Translation","code":"https://github.com/facebookresearch/fairseq","n_code_links":2,"syntology":null},{"rank_in_archive_order":47,"model":"LSTM","metrics":{"BLEU score":"34.8"},"uses_additional_data":false,"paper_date":"2014-09-10","paper":"/paper/sequence-to-sequence-learning-with-neural","paper_url":"http://arxiv.org/abs/1409.3215v3","paper_title":"Sequence to Sequence Learning with Neural Networks","code":"https://github.com/bentrevett/pytorch-seq2seq","n_code_links":74,"syntology":{"n_ran":14,"n_unverified":11,"n_samples":25,"n_pointer_only_licence":9}},{"rank_in_archive_order":48,"model":"CSLM + RNN + WP","metrics":{"BLEU score":"34.54"},"uses_additional_data":false,"paper_date":"2014-06-03","paper":"/paper/learning-phrase-representations-using-rnn","paper_url":"http://arxiv.org/abs/1406.1078v3","paper_title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","code":"https://github.com/graykode/nlp-tutorial","n_code_links":42,"syntology":{"n_ran":13,"n_unverified":9,"n_samples":22,"n_pointer_only_licence":14}},{"rank_in_archive_order":49,"model":"FLAN 137B (zero-shot)","metrics":{"BLEU score":"33.9"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"FLAN 137B (few-shot, k=9)","metrics":{"BLEU score":"33.8"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"Regularized LSTM","metrics":{"BLEU score":"29.03"},"uses_additional_data":false,"paper_date":"2014-09-08","paper":"/paper/recurrent-neural-network-regularization","paper_url":"http://arxiv.org/abs/1409.2329v5","paper_title":"Recurrent Neural Network Regularization","code":"https://github.com/wojzaremba/lstm","n_code_links":21,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":52,"model":"Unsupervised PBSMT","metrics":{"BLEU score":"28.11"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/phrase-based-neural-unsupervised-machine","paper_url":"http://arxiv.org/abs/1804.07755v2","paper_title":"Phrase-Based & Neural Unsupervised Machine Translation","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":null},{"rank_in_archive_order":53,"model":"PBSMT + NMT","metrics":{"BLEU score":"27.6"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/phrase-based-neural-unsupervised-machine","paper_url":"http://arxiv.org/abs/1804.07755v2","paper_title":"Phrase-Based & Neural Unsupervised Machine Translation","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":null},{"rank_in_archive_order":54,"model":"GRU+Attention","metrics":{"BLEU score":"26.4"},"uses_additional_data":false,"paper_date":"2016-10-27","paper":"/paper/can-active-memory-replace-attention","paper_url":"http://arxiv.org/abs/1610.08613v2","paper_title":"Can Active Memory Replace Attention?","code":"https://github.com/tensorflow/models","n_code_links":2,"syntology":null},{"rank_in_archive_order":55,"model":"SMT + iterative backtranslation (unsupervised)","metrics":{"BLEU score":"26.22"},"uses_additional_data":false,"paper_date":"2018-09-04","paper":"/paper/unsupervised-statistical-machine-translation","paper_url":"http://arxiv.org/abs/1809.01272v1","paper_title":"Unsupervised Statistical Machine Translation","code":"https://github.com/artetxem/vecmap","n_code_links":3,"syntology":null},{"rank_in_archive_order":56,"model":"Unsupervised NMT + Transformer","metrics":{"BLEU score":"25.14"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/phrase-based-neural-unsupervised-machine","paper_url":"http://arxiv.org/abs/1804.07755v2","paper_title":"Phrase-Based & Neural Unsupervised Machine Translation","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":null},{"rank_in_archive_order":57,"model":"Unsupervised attentional encoder-decoder + BPE","metrics":{"BLEU score":"14.36"},"uses_additional_data":false,"paper_date":"2017-10-30","paper":"/paper/unsupervised-neural-machine-translation","paper_url":"http://arxiv.org/abs/1710.11041v2","paper_title":"Unsupervised Neural Machine Translation","code":"https://github.com/rsennrich/subword-nmt","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":27,"rows_with_any_sample_ran":24,"distinct_papers_with_graph_line":22,"distinct_papers_with_any_sample_ran":20,"samples_over_distinct_papers":{"n_ran":764,"n_unverified":445,"n_samples":1209,"n_pointer_only_licence":536,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1401,"n_unverified":796,"n_samples":2197,"n_pointer_only_licence":996,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}