{"url":"/task/machine-translation","name":"Machine Translation","slug":"machine-translation","description_markdown":"**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>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":10752,"papers_with_code":2444,"benchmarks":84,"benchmark_tables_in_archive":84,"benchmark_tables_shown":84,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":82,"subtasks":10,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","slug":"machine-translation-on-wmt2014-english-german","dataset":"WMT2014 English-German","dataset_url":"/dataset/wmt-2014","rows_in_archive":91,"metrics":["BLEU score","SacreBLEU","Number of Params","Hardware Burden","Operations per network pass"],"first_row_in_archive_order":{"model":"Transformer Cycle (Rev)","paper_title":"Lessons on Parameter Sharing across Layers in Transformers","paper_url":"/paper/lessons-on-parameter-sharing-across-layers-in","paper_date":"2021-04-13","arxiv_id":"2104.06022","code_links":[{"title":"takase/share_layer_params","url":"https://github.com/takase/share_layer_params"},{"title":"jaketae/param-share-transformer","url":"https://github.com/jaketae/param-share-transformer"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","slug":"machine-translation-on-wmt2014-english-french","dataset":"WMT2014 English-French","dataset_url":"/dataset/wmt-2014","rows_in_archive":57,"metrics":["BLEU score","SacreBLEU","Hardware Burden","Operations per network pass"],"first_row_in_archive_order":{"model":"Transformer+BT (ADMIN init)","paper_title":"Very Deep Transformers for Neural Machine Translation","paper_url":"/paper/very-deep-transformers-for-neural-machine","paper_date":"2020-08-18","arxiv_id":"2008.07772","code_links":[{"title":"LiyuanLucasLiu/Transforemr-Clinic","url":"https://github.com/LiyuanLucasLiu/Transforemr-Clinic"},{"title":"LiyuanLucasLiu/Transformer-Clinic","url":"https://github.com/LiyuanLucasLiu/Transformer-Clinic"},{"title":"microsoft/deepnmt","url":"https://github.com/microsoft/deepnmt"},{"title":"namisan/exdeep-nmt","url":"https://github.com/namisan/exdeep-nmt"}],"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2014-german","slug":"machine-translation-on-iwslt2014-german","dataset":"IWSLT2014 German-English","dataset_url":null,"rows_in_archive":34,"metrics":["BLEU score","Number of Params"],"first_row_in_archive_order":{"model":"PiNMT","paper_title":"Integrating Pre-trained Language Model into Neural Machine Translation","paper_url":"/paper/integrating-pre-trained-language-model-into","paper_date":"2023-10-30","arxiv_id":"2310.19680","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-aces","slug":"machine-translation-on-aces","dataset":"ACES","dataset_url":"/dataset/aces","rows_in_archive":21,"metrics":["Score"],"first_row_in_archive_order":{"model":"HWTSC-Teacher-Sim","paper_title":"ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metrics","paper_url":"/paper/aces-translation-accuracy-challenge-sets-for","paper_date":"2022-10-27","arxiv_id":"2210.15615","code_links":[{"title":"edinburghnlp/aces","url":"https://github.com/edinburghnlp/aces"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","slug":"machine-translation-on-wmt2016-english-1","dataset":"WMT2016 English-Romanian","dataset_url":"/dataset/wmt-2016","rows_in_archive":21,"metrics":["BLEU score","BLEU-4"],"first_row_in_archive_order":{"model":"DeLighT","paper_title":"DeLighT: Deep and Light-weight Transformer","paper_url":"/paper/delight-very-deep-and-light-weight","paper_date":"2020-08-03","arxiv_id":"2008.00623","code_links":[{"title":"sacmehta/delight","url":"https://github.com/sacmehta/delight"},{"title":"pranay185417/delight","url":"https://github.com/pranay185417/delight"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","slug":"machine-translation-on-wmt2016-romanian","dataset":"WMT2016 Romanian-English","dataset_url":"/dataset/wmt-2016","rows_in_archive":21,"metrics":["BLEU score","BLEU-4"],"first_row_in_archive_order":{"model":"fast-noisy-channel-modeling","paper_title":"Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling","paper_url":"/paper/language-models-not-just-for-pre-training","paper_date":"2020-11-13","arxiv_id":"2011.07164","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/fast_noisy_channel"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","slug":"machine-translation-on-wmt2014-german-english","dataset":"WMT2014 German-English","dataset_url":"/dataset/wmt-2014","rows_in_archive":16,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Bi-SimCut","paper_title":"Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation","paper_url":"/paper/bi-simcut-a-simple-strategy-for-boosting-1","paper_date":"2022-06-06","arxiv_id":"2206.02368","code_links":[{"title":"gpengzhi/Bi-SimCut","url":"https://github.com/gpengzhi/Bi-SimCut"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt2015-german","slug":"machine-translation-on-iwslt2015-german","dataset":"IWSLT2015 German-English","dataset_url":null,"rows_in_archive":15,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"PS-KD","paper_title":"Self-Knowledge Distillation with Progressive Refinement of Targets","paper_url":"/paper/self-knowledge-distillation-a-simple-way-for","paper_date":"2020-06-22","arxiv_id":"2006.12000","code_links":[{"title":"lgcnsai/ps-kd-pytorch","url":"https://github.com/lgcnsai/ps-kd-pytorch"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-german","slug":"machine-translation-on-wmt2016-english-german","dataset":"WMT2016 English-German","dataset_url":"/dataset/wmt-2016","rows_in_archive":12,"metrics":["BLEU score","SacreBLEU"],"first_row_in_archive_order":{"model":"MADL","paper_title":"Multi-Agent Dual Learning","paper_url":"/paper/multi-agent-dual-learning","paper_date":"2019-05-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt2015-english-1","slug":"machine-translation-on-iwslt2015-english-1","dataset":"IWSLT2015 English-Vietnamese","dataset_url":null,"rows_in_archive":11,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"EnViT5 + MTet","paper_title":"MTet: Multi-domain Translation for English and Vietnamese","paper_url":"/paper/mtet-multi-domain-translation-for-english-and","paper_date":"2022-10-11","arxiv_id":"2210.05610","code_links":[{"title":"vietai/mTet","url":"https://github.com/vietai/mTet"},{"title":"vietai/SAT","url":"https://github.com/vietai/SAT"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt2015-english","slug":"machine-translation-on-iwslt2015-english","dataset":"IWSLT2015 English-German","dataset_url":null,"rows_in_archive":8,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"PS-KD","paper_title":"Self-Knowledge Distillation with Progressive Refinement of Targets","paper_url":"/paper/self-knowledge-distillation-a-simple-way-for","paper_date":"2020-06-22","arxiv_id":"2006.12000","code_links":[{"title":"lgcnsai/ps-kd-pytorch","url":"https://github.com/lgcnsai/ps-kd-pytorch"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-german-english","slug":"machine-translation-on-wmt2016-german-english","dataset":"WMT2016 German-English","dataset_url":"/dataset/wmt-2016","rows_in_archive":8,"metrics":["BLEU score","SacreBLEU"],"first_row_in_archive_order":{"model":"FLAN 137B (few-shot, k=11)","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_url":"/paper/finetuned-language-models-are-zero-shot","paper_date":"2021-09-03","arxiv_id":"2109.01652","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2014-english","slug":"machine-translation-on-iwslt2014-english","dataset":"IWSLT2014 English-German","dataset_url":null,"rows_in_archive":6,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"PiNMT","paper_title":"Integrating Pre-trained Language Model into Neural Machine Translation","paper_url":"/paper/integrating-pre-trained-language-model-into","paper_date":"2023-10-30","arxiv_id":"2310.19680","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2015-english-german","slug":"machine-translation-on-wmt2015-english-german","dataset":"WMT2015 English-German","dataset_url":"/dataset/wmt-2015","rows_in_archive":6,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"ByteNet","paper_title":"Neural Machine Translation in Linear Time","paper_url":"/paper/neural-machine-translation-in-linear-time","paper_date":"2016-10-31","arxiv_id":"1610.10099","code_links":[{"title":"paarthneekhara/byteNet-tensorflow","url":"https://github.com/paarthneekhara/byteNet-tensorflow"},{"title":"microsoft/protein-sequence-models","url":"https://github.com/microsoft/protein-sequence-models"},{"title":"randomrandom/deep-atrous-cnn-sentiment","url":"https://github.com/randomrandom/deep-atrous-cnn-sentiment"},{"title":"kingstarcraft/speech-to-text-wavenet2","url":"https://github.com/kingstarcraft/speech-to-text-wavenet2"},{"title":"sriharireddypusapati/speech-to-text-wavenet2","url":"https://github.com/sriharireddypusapati/speech-to-text-wavenet2"},{"title":"kinimod23/ATS_Project","url":"https://github.com/kinimod23/ATS_Project"},{"title":"Vikas-Sony/speech-to-text","url":"https://github.com/Vikas-Sony/speech-to-text"},{"title":"freedombenLiu/speech-to-text-wavenet","url":"https://github.com/freedombenLiu/speech-to-text-wavenet"},{"title":"adityaagrawal7/speech-to-text-wavenet","url":"https://github.com/adityaagrawal7/speech-to-text-wavenet"},{"title":"liguigui/speech-to-text-wavenet","url":"https://github.com/liguigui/speech-to-text-wavenet"},{"title":"Shivendra-psc/speechbot","url":"https://github.com/Shivendra-psc/speechbot"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-flores-200","slug":"machine-translation-on-flores-200","dataset":"FLoRes-200","dataset_url":"/dataset/flores-200","rows_in_archive":5,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"GenTranslate-7B","paper_title":"GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators","paper_url":"/paper/gentranslate-large-language-models-are","paper_date":"2024-02-10","arxiv_id":"2402.06894","code_links":[{"title":"yuchen005/gentranslate","url":"https://github.com/yuchen005/gentranslate"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2017-latvian","slug":"machine-translation-on-wmt-2017-latvian","dataset":"WMT 2017 Latvian-English","dataset_url":null,"rows_in_archive":4,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Transformer trained on highly filtered data","paper_title":"Impact of Corpora Quality on Neural Machine Translation","paper_url":"/paper/impact-of-corpora-quality-on-neural-machine","paper_date":"2018-10-19","arxiv_id":"1810.08392","code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2016-english","slug":"machine-translation-on-wmt2016-english","dataset":"WMT2016 English-Russian","dataset_url":"/dataset/wmt-2016","rows_in_archive":4,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper_title":"Edinburgh Neural Machine Translation Systems for WMT 16","paper_url":"/paper/edinburgh-neural-machine-translation-systems","paper_date":"2016-06-09","arxiv_id":"1606.02891","code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-eng-x","slug":"machine-translation-on-flores95-devtest-eng-x","dataset":"flores95-devtest eng-X","dataset_url":null,"rows_in_archive":3,"metrics":["ChrF++"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper_title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","paper_url":"/paper/seamlessm4t-massively-multilingual-multimodal","paper_date":"2023-08-22","arxiv_id":"2308.11596","code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-x-eng","slug":"machine-translation-on-flores95-devtest-x-eng","dataset":"flores95-devtest X-eng","dataset_url":null,"rows_in_archive":3,"metrics":["ChrF++"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper_title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","paper_url":"/paper/seamlessm4t-massively-multilingual-multimodal","paper_date":"2023-08-22","arxiv_id":"2308.11596","code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/machine-translation-on-frmt-chinese-mainland","slug":"machine-translation-on-frmt-chinese-mainland","dataset":"FRMT (Chinese - Mainland)","dataset_url":"/dataset/frmt","rows_in_archive":3,"metrics":["BLEURT"],"first_row_in_archive_order":{"model":"PaLM 2","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-frmt-chinese-taiwan","slug":"machine-translation-on-frmt-chinese-taiwan","dataset":"FRMT (Chinese - Taiwan)","dataset_url":"/dataset/frmt","rows_in_archive":3,"metrics":["BLEURT"],"first_row_in_archive_order":{"model":"PaLM 2","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-frmt-portuguese","slug":"machine-translation-on-frmt-portuguese","dataset":"FRMT (Portuguese - Portugal)","dataset_url":"/dataset/frmt","rows_in_archive":3,"metrics":["BLEURT"],"first_row_in_archive_order":{"model":"PaLM 2","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-frmt-portuguese-brazil","slug":"machine-translation-on-frmt-portuguese-brazil","dataset":"FRMT (Portuguese - Brazil)","dataset_url":"/dataset/frmt","rows_in_archive":3,"metrics":["BLEURT"],"first_row_in_archive_order":{"model":"PaLM 2","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2017-english-1","slug":"machine-translation-on-wmt-2017-english-1","dataset":"WMT 2017 English-Chinese","dataset_url":null,"rows_in_archive":3,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"DynamicConv","paper_title":"Pay Less Attention with Lightweight and Dynamic Convolutions","paper_url":"/paper/pay-less-attention-with-lightweight-and","paper_date":"2019-01-29","arxiv_id":"1901.10430","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"},{"title":"bytedance/neurst","url":"https://github.com/bytedance/neurst"},{"title":"dqqcasia/st","url":"https://github.com/dqqcasia/st"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2014-french-english","slug":"machine-translation-on-wmt2014-french-english","dataset":"WMT2014 French-English","dataset_url":"/dataset/wmt-2014","rows_in_archive":3,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"FLAN 137B (few-shot, k=9)","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_url":"/paper/finetuned-language-models-are-zero-shot","paper_date":"2021-09-03","arxiv_id":"2109.01652","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2017-chinese","slug":"machine-translation-on-wmt2017-chinese","dataset":"WMT2017 Chinese-English","dataset_url":null,"rows_in_archive":3,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"StrokeNet","paper_title":"Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling","paper_url":"/paper/breaking-the-representation-bottleneck-of","paper_date":"2022-11-23","arxiv_id":"2211.12781","code_links":[{"title":"zjwang21/strokenet","url":"https://github.com/zjwang21/strokenet"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-20news","slug":"machine-translation-on-20news","dataset":"20NEWS","dataset_url":null,"rows_in_archive":2,"metrics":["1-of-100 Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"tensorflow/tensor2tensor","paper_title":"Neural Machine Translation","paper_url":"/paper/neural-machine-translation","paper_date":"2017-09-22","arxiv_id":"1709.07809","code_links":[{"title":"tensorflow/tensor2tensor","url":"https://github.com/tensorflow/tensor2tensor"},{"title":"awslabs/sockeye","url":"https://github.com/awslabs/sockeye"},{"title":"EdinburghNLP/nematus","url":"https://github.com/EdinburghNLP/nematus"},{"title":"neulab/xnmt","url":"https://github.com/neulab/xnmt"},{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-arba-sicula","slug":"machine-translation-on-arba-sicula","dataset":"Arba Sicula","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU (En-Scn)","BLEU (It-Scn)","BLEU (Scn-En)","BLEU (Scn-It)"],"first_row_in_archive_order":{"model":"Larger","paper_title":"Sicilian Translator: A Recipe for Low-Resource NMT","paper_url":"/paper/sicilian-translator-a-recipe-for-low-resource","paper_date":"2021-10-05","arxiv_id":"2110.01938","code_links":[{"title":"ewdowiak/Sicilian_Translator","url":"https://github.com/ewdowiak/Sicilian_Translator"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-itihasa","slug":"machine-translation-on-itihasa","dataset":"Itihasa","dataset_url":"/dataset/itihasa","rows_in_archive":2,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Baseline (en->sn)","paper_title":"Itihasa: A large-scale corpus for Sanskrit to English translation","paper_url":"/paper/itihasa-a-large-scale-corpus-for-sanskrit-to","paper_date":"2021-06-06","arxiv_id":"2106.03269","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt2015-vietnamese","slug":"machine-translation-on-iwslt2015-vietnamese","dataset":"IWSLT2015 Vietnamese-English","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"HeadMask (Random-18)","paper_title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","paper_url":"/paper/alleviating-the-inequality-of-attention-heads","paper_date":"2020-09-21","arxiv_id":"2009.09672","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt2017-arabic","slug":"machine-translation-on-iwslt2017-arabic","dataset":"IWSLT2017 Arabic-English","dataset_url":null,"rows_in_archive":2,"metrics":["Cased sacreBLEU","SacreBLEU"],"first_row_in_archive_order":{"model":"Transformer base + BPE-Dropout","paper_title":"BPE-Dropout: Simple and Effective Subword Regularization","paper_url":"/paper/191013267","paper_date":"2019-10-29","arxiv_id":"1910.13267","code_links":[{"title":"google/sentencepiece","url":"https://github.com/google/sentencepiece"},{"title":"rsennrich/subword-nmt","url":"https://github.com/rsennrich/subword-nmt"},{"title":"VKCOM/YouTokenToMe","url":"https://github.com/VKCOM/YouTokenToMe"},{"title":"VProv/BPE-Dropout","url":"https://github.com/VProv/BPE-Dropout"},{"title":"kh-mo/QA_wikisql","url":"https://github.com/kh-mo/QA_wikisql"},{"title":"mozilla/subword-nmt","url":"https://github.com/mozilla/subword-nmt"},{"title":"PatxiofromAlphensign/subword-nmt-mods","url":"https://github.com/PatxiofromAlphensign/subword-nmt-mods"}],"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2017-english","slug":"machine-translation-on-iwslt2017-english","dataset":"IWSLT2017 English-French","dataset_url":null,"rows_in_archive":2,"metrics":["Cased sacreBLEU","SacreBLEU"],"first_row_in_archive_order":{"model":"Transformer base + BPE-Dropout","paper_title":"BPE-Dropout: Simple and Effective Subword Regularization","paper_url":"/paper/191013267","paper_date":"2019-10-29","arxiv_id":"1910.13267","code_links":[{"title":"google/sentencepiece","url":"https://github.com/google/sentencepiece"},{"title":"rsennrich/subword-nmt","url":"https://github.com/rsennrich/subword-nmt"},{"title":"VKCOM/YouTokenToMe","url":"https://github.com/VKCOM/YouTokenToMe"},{"title":"VProv/BPE-Dropout","url":"https://github.com/VProv/BPE-Dropout"},{"title":"kh-mo/QA_wikisql","url":"https://github.com/kh-mo/QA_wikisql"},{"title":"mozilla/subword-nmt","url":"https://github.com/mozilla/subword-nmt"},{"title":"PatxiofromAlphensign/subword-nmt-mods","url":"https://github.com/PatxiofromAlphensign/subword-nmt-mods"}],"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2017-english-1","slug":"machine-translation-on-iwslt2017-english-1","dataset":"IWSLT2017 English-Arabic","dataset_url":null,"rows_in_archive":2,"metrics":["Cased sacreBLEU","SacreBLEU"],"first_row_in_archive_order":{"model":"Transformer base + BPE-Dropout","paper_title":"BPE-Dropout: Simple and Effective Subword Regularization","paper_url":"/paper/191013267","paper_date":"2019-10-29","arxiv_id":"1910.13267","code_links":[{"title":"google/sentencepiece","url":"https://github.com/google/sentencepiece"},{"title":"rsennrich/subword-nmt","url":"https://github.com/rsennrich/subword-nmt"},{"title":"VKCOM/YouTokenToMe","url":"https://github.com/VKCOM/YouTokenToMe"},{"title":"VProv/BPE-Dropout","url":"https://github.com/VProv/BPE-Dropout"},{"title":"kh-mo/QA_wikisql","url":"https://github.com/kh-mo/QA_wikisql"},{"title":"mozilla/subword-nmt","url":"https://github.com/mozilla/subword-nmt"},{"title":"PatxiofromAlphensign/subword-nmt-mods","url":"https://github.com/PatxiofromAlphensign/subword-nmt-mods"}],"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2017-french","slug":"machine-translation-on-iwslt2017-french","dataset":"IWSLT2017 French-English","dataset_url":null,"rows_in_archive":2,"metrics":["Cased sacreBLEU","SacreBLEU"],"first_row_in_archive_order":{"model":"Transformer base + BPE-Dropout","paper_title":"BPE-Dropout: Simple and Effective Subword Regularization","paper_url":"/paper/191013267","paper_date":"2019-10-29","arxiv_id":"1910.13267","code_links":[{"title":"google/sentencepiece","url":"https://github.com/google/sentencepiece"},{"title":"rsennrich/subword-nmt","url":"https://github.com/rsennrich/subword-nmt"},{"title":"VKCOM/YouTokenToMe","url":"https://github.com/VKCOM/YouTokenToMe"},{"title":"VProv/BPE-Dropout","url":"https://github.com/VProv/BPE-Dropout"},{"title":"kh-mo/QA_wikisql","url":"https://github.com/kh-mo/QA_wikisql"},{"title":"mozilla/subword-nmt","url":"https://github.com/mozilla/subword-nmt"},{"title":"PatxiofromAlphensign/subword-nmt-mods","url":"https://github.com/PatxiofromAlphensign/subword-nmt-mods"}],"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2017-german","slug":"machine-translation-on-iwslt2017-german","dataset":"IWSLT2017 German-English","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Adaptively Sparse Transformer (alpha-entmax)","paper_title":"Adaptively Sparse Transformers","paper_url":"/paper/adaptively-sparse-transformers","paper_date":"2019-08-30","arxiv_id":"1909.00015","code_links":[{"title":"deep-spin/entmax","url":"https://github.com/deep-spin/entmax"},{"title":"prajjwal1/fluence","url":"https://github.com/prajjwal1/fluence"},{"title":"prajjwal1/adaptive_transformer","url":"https://github.com/prajjwal1/adaptive_transformer"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt-2018-finnish","slug":"machine-translation-on-wmt-2018-finnish","dataset":"WMT 2018 Finnish-English","dataset_url":"/dataset/wmt-2018","rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"CT+B/S construction","paper_title":"The University of Sydney's Machine Translation System for WMT19","paper_url":"/paper/the-university-of-sydneys-machine-translation","paper_date":"2019-06-30","arxiv_id":"1907.00494","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-czech","slug":"machine-translation-on-wmt2014-english-czech","dataset":"WMT2014 English-Czech","dataset_url":"/dataset/wmt-2014","rows_in_archive":2,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Evolved Transformer Big","paper_title":"The Evolved Transformer","paper_url":"/paper/the-evolved-transformer","paper_date":"2019-01-30","arxiv_id":"1901.11117","code_links":[{"title":"tensorflow/tensor2tensor","url":"https://github.com/tensorflow/tensor2tensor"},{"title":"nazarov-yuriy/zh-ru-shared-task","url":"https://github.com/nazarov-yuriy/zh-ru-shared-task"},{"title":"moon23k/Transformer_Archs","url":"https://github.com/moon23k/Transformer_Archs"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2017-turkish","slug":"machine-translation-on-wmt2017-turkish","dataset":"WMT2017 Turkish-English","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"HeadMask (Random-18)","paper_title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","paper_url":"/paper/alleviating-the-inequality-of-attention-heads","paper_date":"2020-09-21","arxiv_id":"2009.09672","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2019-english-german","slug":"machine-translation-on-wmt2019-english-german","dataset":"WMT2019 English-German","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU score","SacreBLEU"],"first_row_in_archive_order":{"model":"Facebook FAIR (ensemble)","paper_title":"Facebook FAIR's WMT19 News Translation Task Submission","paper_url":"/paper/facebook-fairs-wmt19-news-translation-task","paper_date":"2019-07-15","arxiv_id":"1907.06616","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/wmt19"},{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"cyberagentailab/mbr-anomaly","url":"https://github.com/cyberagentailab/mbr-anomaly"},{"title":"atreyasha/semantic-isometry-nmt","url":"https://github.com/atreyasha/semantic-isometry-nmt"}],"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-accurat-balanced-test-1","slug":"machine-translation-on-accurat-balanced-test-1","dataset":"ACCURAT balanced test corpus for under resourced languages Russian-Estonian","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Multilingual Transformer","paper_title":"Training and Adapting Multilingual NMT for Less-resourced and Morphologically Rich Languages","paper_url":"/paper/training-and-adapting-multilingual-nmt-for","paper_date":"2018-05-01","arxiv_id":null,"code_links":[{"title":"tilde-nlp/multilingual-nmt-data-prep","url":"https://github.com/tilde-nlp/multilingual-nmt-data-prep"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-accurat-balanced-test-2","slug":"machine-translation-on-accurat-balanced-test-2","dataset":"ACCURAT balanced test corpus for under resourced languages Estonian-Russian","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Multilingual Transformer","paper_title":"Training and Adapting Multilingual NMT for Less-resourced and Morphologically Rich Languages","paper_url":"/paper/training-and-adapting-multilingual-nmt-for","paper_date":"2018-05-01","arxiv_id":null,"code_links":[{"title":"tilde-nlp/multilingual-nmt-data-prep","url":"https://github.com/tilde-nlp/multilingual-nmt-data-prep"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-alexa-point-of-view","slug":"machine-translation-on-alexa-point-of-view","dataset":"Alexa Point of View","dataset_url":"/dataset/alexa-point-of-view","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"T5","paper_title":"Converting the Point of View of Messages Spoken to Virtual Assistants","paper_url":"/paper/converting-the-point-of-view-of-messages","paper_date":"2020-10-06","arxiv_id":"2010.02600","code_links":[{"title":"alexa/alexa-point-of-view-dataset","url":"https://github.com/alexa/alexa-point-of-view-dataset"},{"title":"prithviraj-maurya/alexa-point-of-view-dataset","url":"https://github.com/prithviraj-maurya/alexa-point-of-view-dataset"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-business-scene","slug":"machine-translation-on-business-scene","dataset":"Business Scene Dialogue JA-EN","dataset_url":"/dataset/business-scene-dialogue","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Transformer-base","paper_title":"Designing the Business Conversation Corpus","paper_url":"/paper/designing-the-business-conversation-corpus-1","paper_date":"2020-08-05","arxiv_id":"2008.01940","code_links":[{"title":"tsuruoka-lab/BSD","url":"https://github.com/tsuruoka-lab/BSD"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-business-scene-1","slug":"machine-translation-on-business-scene-1","dataset":"Business Scene Dialogue EN-JA","dataset_url":"/dataset/business-scene-dialogue","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Transformer-base","paper_title":"Designing the Business Conversation Corpus","paper_url":"/paper/designing-the-business-conversation-corpus-1","paper_date":"2020-08-05","arxiv_id":"2008.01940","code_links":[{"title":"tsuruoka-lab/BSD","url":"https://github.com/tsuruoka-lab/BSD"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt-2017","slug":"machine-translation-on-iwslt-2017","dataset":"IWSLT 2017","dataset_url":"/dataset/iwslt-2017","rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"GPT-4o (HPT)","paper_title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","paper_url":"/paper/hierarchical-prompting-taxonomy-a-universal","paper_date":"2024-06-18","arxiv_id":"2406.12644","code_links":[{"title":"devichand579/HPT","url":"https://github.com/devichand579/HPT"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-iwslt2015-chinese","slug":"machine-translation-on-iwslt2015-chinese","dataset":"IWSLT2015 Chinese-English","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"BP-Transformer","paper_title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","paper_url":"/paper/bp-transformer-modelling-long-range-context","paper_date":"2019-11-11","arxiv_id":"1911.04070","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/transformer"},{"title":"yzh119/BPT","url":"https://github.com/yzh119/BPT"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-iwslt2015-thai-english","slug":"machine-translation-on-iwslt2015-thai-english","dataset":"IWSLT2015 Thai-English","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Seq-KD + Seq-Inter + Word-KD","paper_title":"Sequence-Level Knowledge Distillation","paper_url":"/paper/sequence-level-knowledge-distillation","paper_date":"2016-06-25","arxiv_id":"1606.07947","code_links":[{"title":"harvardnlp/seq2seq-attn","url":"https://github.com/harvardnlp/seq2seq-attn"},{"title":"facebookresearch/stopes","url":"https://github.com/facebookresearch/stopes"},{"title":"harvardnlp/nmt-android","url":"https://github.com/harvardnlp/nmt-android"},{"title":"ictnlp/Seq-NAT","url":"https://github.com/ictnlp/Seq-NAT"},{"title":"xuanlinli17/autoregressive_inference","url":"https://github.com/xuanlinli17/autoregressive_inference"},{"title":"anonymouscode115/autoregressive_inference","url":"https://github.com/anonymouscode115/autoregressive_inference"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-multi-lingual-bug","slug":"machine-translation-on-multi-lingual-bug","dataset":"Multi Lingual Bug Reports","dataset_url":"/dataset/multi-lingual-bug-reports","rows_in_archive":1,"metrics":["BERTScore"],"first_row_in_archive_order":{"model":"ChatGPT","paper_title":"English Please: Evaluating Machine Translation with Large Language Models for Multilingual Bug Reports","paper_url":"/paper/english-please-evaluating-machine-translation","paper_date":"2025-02-20","arxiv_id":"2502.14338","code_links":[{"title":"av9ash/English-Please","url":"https://github.com/av9ash/English-Please"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-opensubtitles","slug":"machine-translation-on-opensubtitles","dataset":"OpenSubtitles","dataset_url":"/dataset/opensubtitles","rows_in_archive":1,"metrics":["BLEU score","METEOR"],"first_row_in_archive_order":{"model":"Fine tuned MarianMT","paper_title":"Crossing Language Borders: A Pipeline for Indonesian Manhwa Translation","paper_url":"/paper/crossing-language-borders-a-pipeline-for","paper_date":"2025-01-03","arxiv_id":"2501.01629","code_links":[{"title":"Sagarika-Singh-99/indonesian_manhwa_translation","url":"https://github.com/Sagarika-Singh-99/indonesian_manhwa_translation"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-slone-myv-ru-2022-myv","slug":"machine-translation-on-slone-myv-ru-2022-myv","dataset":"slone/myv_ru_2022 myv-ru","dataset_url":null,"rows_in_archive":1,"metrics":["ChrF++"],"first_row_in_archive_order":{"model":"slone/mbart-large-51-myv-mul-v1","paper_title":"The first neural machine translation system for the Erzya language","paper_url":"/paper/the-first-neural-machine-translation-system","paper_date":"2022-09-19","arxiv_id":"2209.09368","code_links":[{"title":"slone-nlp/myv-nmt","url":"https://github.com/slone-nlp/myv-nmt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-slone-myv-ru-2022-ru","slug":"machine-translation-on-slone-myv-ru-2022-ru","dataset":"slone/myv_ru_2022 ru-myv","dataset_url":null,"rows_in_archive":1,"metrics":["ChrF++"],"first_row_in_archive_order":{"model":"slone/mbart-large-51-mul-myv-v1","paper_title":"The first neural machine translation system for the Erzya language","paper_url":"/paper/the-first-neural-machine-translation-system","paper_date":"2022-09-19","arxiv_id":"2209.09368","code_links":[{"title":"slone-nlp/myv-nmt","url":"https://github.com/slone-nlp/myv-nmt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-tatoeba-el-to-en","slug":"machine-translation-on-tatoeba-el-to-en","dataset":"Tatoeba (EL-to-EN)","dataset_url":"/dataset/tatoeba","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"PENELOPIE (Transformers-based Greek-to-English NMT)","paper_title":"PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation","paper_url":"/paper/penelopie-enabling-open-information","paper_date":"2021-03-28","arxiv_id":"2103.15075","code_links":[{"title":"lighteternal/PENELOPIE","url":"https://github.com/lighteternal/PENELOPIE"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-tatoeba-en-to-el","slug":"machine-translation-on-tatoeba-en-to-el","dataset":"Tatoeba (EN-to-EL)","dataset_url":"/dataset/tatoeba","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"PENELOPIE Transformers-based NMT (EN2EL)","paper_title":"PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation","paper_url":"/paper/penelopie-enabling-open-information","paper_date":"2021-03-28","arxiv_id":"2103.15075","code_links":[{"title":"lighteternal/PENELOPIE","url":"https://github.com/lighteternal/PENELOPIE"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-v-a-trained-on-t-h","slug":"machine-translation-on-v-a-trained-on-t-h","dataset":"V_A (trained on T_H)","dataset_url":null,"rows_in_archive":1,"metrics":["Median Relative Edit Distance"],"first_row_in_archive_order":{"model":"M_C","paper_title":"On Automatic Parsing of Log Records","paper_url":"/paper/on-automatic-parsing-of-log-records","paper_date":"2021-02-12","arxiv_id":"2102.06320","code_links":[{"title":"WulffHunter/log_generator","url":"https://github.com/WulffHunter/log_generator"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-v-b-trained-on-t-h","slug":"machine-translation-on-v-b-trained-on-t-h","dataset":"V_B (trained on T_H)","dataset_url":null,"rows_in_archive":1,"metrics":["Median Relative Edit Distance"],"first_row_in_archive_order":{"model":"M_C","paper_title":"On Automatic Parsing of Log Records","paper_url":"/paper/on-automatic-parsing-of-log-records","paper_date":"2021-02-12","arxiv_id":"2102.06320","code_links":[{"title":"WulffHunter/log_generator","url":"https://github.com/WulffHunter/log_generator"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-v-c-trained-on-t-h","slug":"machine-translation-on-v-c-trained-on-t-h","dataset":"V_C (trained on T_H)","dataset_url":null,"rows_in_archive":1,"metrics":["Median Relative Edit Distance"],"first_row_in_archive_order":{"model":"M_C","paper_title":"On Automatic Parsing of Log Records","paper_url":"/paper/on-automatic-parsing-of-log-records","paper_date":"2021-02-12","arxiv_id":"2102.06320","code_links":[{"title":"WulffHunter/log_generator","url":"https://github.com/WulffHunter/log_generator"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2017-english","slug":"machine-translation-on-wmt-2017-english","dataset":"WMT 2017 English-Latvian","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Transformer trained on highly filtered data","paper_title":"Impact of Corpora Quality on Neural Machine Translation","paper_url":"/paper/impact-of-corpora-quality-on-neural-machine","paper_date":"2018-10-19","arxiv_id":"1810.08392","code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2018-english","slug":"machine-translation-on-wmt-2018-english","dataset":"WMT 2018 English-Estonian","dataset_url":"/dataset/wmt-2018","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Multi-pass backtranslated adapted transformer","paper_title":"Tilde's Machine Translation Systems for WMT 2018","paper_url":"/paper/tildes-machine-translation-systems-for-wmt","paper_date":"2018-10-01","arxiv_id":null,"code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2018-english-1","slug":"machine-translation-on-wmt-2018-english-1","dataset":"WMT 2018 English-Finnish","dataset_url":"/dataset/wmt-2018","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Transformer trained on highly filtered data","paper_title":"Impact of Corpora Quality on Neural Machine Translation","paper_url":"/paper/impact-of-corpora-quality-on-neural-machine","paper_date":"2018-10-19","arxiv_id":"1810.08392","code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2018-estonian","slug":"machine-translation-on-wmt-2018-estonian","dataset":"WMT 2018 Estonian-English","dataset_url":"/dataset/wmt-2018","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Multi-pass backtranslated adapted transformer","paper_title":"Tilde's Machine Translation Systems for WMT 2018","paper_url":"/paper/tildes-machine-translation-systems-for-wmt","paper_date":"2018-10-01","arxiv_id":null,"code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-chinese","slug":"machine-translation-on-wmt-2022-chinese","dataset":"WMT 2022 Chinese-English","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-czech-english","slug":"machine-translation-on-wmt-2022-czech-english","dataset":"WMT 2022 Czech-English","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-english","slug":"machine-translation-on-wmt-2022-english","dataset":"WMT 2022 English-German","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-english-1","slug":"machine-translation-on-wmt-2022-english-1","dataset":"WMT 2022 English-Japanese","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-english-2","slug":"machine-translation-on-wmt-2022-english-2","dataset":"WMT 2022 English-Russian","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-english-3","slug":"machine-translation-on-wmt-2022-english-3","dataset":"WMT 2022 English-Chinese","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-english-czech","slug":"machine-translation-on-wmt-2022-english-czech","dataset":"WMT 2022 English-Czech","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-german","slug":"machine-translation-on-wmt-2022-german","dataset":"WMT 2022 German-English","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-japanese","slug":"machine-translation-on-wmt-2022-japanese","dataset":"WMT 2022 Japanese-English","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt-2022-russian","slug":"machine-translation-on-wmt-2022-russian","dataset":"WMT 2022 Russian-English","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Vega-MT","paper_title":"Vega-MT: The JD Explore Academy Translation System for WMT22","paper_url":"/paper/vega-mt-the-jd-explore-academy-translation","paper_date":"2022-09-20","arxiv_id":"2209.09444","code_links":[{"title":"jdea-nlp/vega-mt","url":"https://github.com/jdea-nlp/vega-mt"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2015-english","slug":"machine-translation-on-wmt2015-english","dataset":"WMT2015 English-Russian","dataset_url":"/dataset/wmt-2015","rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"C2-50k Segmentation","paper_title":"Neural Machine Translation of Rare Words with Subword Units","paper_url":"/paper/neural-machine-translation-of-rare-words-with","paper_date":"2015-08-31","arxiv_id":"1508.07909","code_links":[{"title":"facebookresearch/fairseq","url":"https://github.com/facebookresearch/fairseq"},{"title":"google/sentencepiece","url":"https://github.com/google/sentencepiece"},{"title":"karpathy/minbpe","url":"https://github.com/karpathy/minbpe"},{"title":"rsennrich/subword-nmt","url":"https://github.com/rsennrich/subword-nmt"},{"title":"VKCOM/YouTokenToMe","url":"https://github.com/VKCOM/YouTokenToMe"},{"title":"glample/fastBPE","url":"https://github.com/glample/fastBPE"},{"title":"salesforce/GeDi","url":"https://github.com/salesforce/GeDi"},{"title":"EdinburghNLP/code-docstring-corpus","url":"https://github.com/EdinburghNLP/code-docstring-corpus"},{"title":"Avmb/code-docstring-corpus","url":"https://github.com/Avmb/code-docstring-corpus"},{"title":"nyu-dl/dl4mt-cdec","url":"https://github.com/nyu-dl/dl4mt-cdec"},{"title":"nyu-dl/dl4mt-c2c","url":"https://github.com/nyu-dl/dl4mt-c2c"},{"title":"ThAIKeras/bert","url":"https://github.com/ThAIKeras/bert"},{"title":"nyu-dl/dl4mt-simul-trans","url":"https://github.com/nyu-dl/dl4mt-simul-trans"},{"title":"Automattic/wp-translate","url":"https://github.com/Automattic/wp-translate"},{"title":"SeonbeomKim/Python-Bype_Pair_Encoding","url":"https://github.com/SeonbeomKim/Python-Bype_Pair_Encoding"},{"title":"thinkwee/DPP_CNN_Summarization","url":"https://github.com/thinkwee/DPP_CNN_Summarization"},{"title":"SeonbeomKim/Python-Byte_Pair_Encoding","url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding"},{"title":"PaulSudarshan/Language-Classification-Using-Naive-Bayes-Algorithm","url":"https://github.com/PaulSudarshan/Language-Classification-Using-Naive-Bayes-Algorithm"},{"title":"johnr0/TaleBrush-backend","url":"https://github.com/johnr0/TaleBrush-backend"},{"title":"kh-mo/QA_wikisql","url":"https://github.com/kh-mo/QA_wikisql"},{"title":"simonjisu/NMT","url":"https://github.com/simonjisu/NMT"},{"title":"siyuofzhou/CNNSeqToSeq","url":"https://github.com/siyuofzhou/CNNSeqToSeq"},{"title":"lkfo415579/MT-Readling-List","url":"https://github.com/lkfo415579/MT-Readling-List"},{"title":"HarshKhandelwal1552/Language_classifier_with_Naive_Bayes","url":"https://github.com/HarshKhandelwal1552/Language_classifier_with_Naive_Bayes"},{"title":"Xinsen-Zhang/transformer","url":"https://github.com/Xinsen-Zhang/transformer"},{"title":"ksulima/Unsupervised-method-to-NPL-Polish-language","url":"https://github.com/ksulima/Unsupervised-method-to-NPL-Polish-language"}],"syntology":{"n":30,"n_ran":21,"n_unverified":9,"n_pointer_only":21}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-czech-english","slug":"machine-translation-on-wmt2016-czech-english","dataset":"WMT2016 Czech-English","dataset_url":"/dataset/wmt-2016","rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper_title":"Edinburgh Neural Machine Translation Systems for WMT 16","paper_url":"/paper/edinburgh-neural-machine-translation-systems","paper_date":"2016-06-09","arxiv_id":"1606.02891","code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-czech","slug":"machine-translation-on-wmt2016-english-czech","dataset":"WMT2016 English-Czech","dataset_url":"/dataset/wmt-2016","rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper_title":"Edinburgh Neural Machine Translation Systems for WMT 16","paper_url":"/paper/edinburgh-neural-machine-translation-systems","paper_date":"2016-06-09","arxiv_id":"1606.02891","code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-french","slug":"machine-translation-on-wmt2016-english-french","dataset":"WMT2016 English-French","dataset_url":"/dataset/wmt-2016","rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"DeLighT","paper_title":"DeLighT: Deep and Light-weight Transformer","paper_url":"/paper/delight-very-deep-and-light-weight","paper_date":"2020-08-03","arxiv_id":"2008.00623","code_links":[{"title":"sacmehta/delight","url":"https://github.com/sacmehta/delight"},{"title":"pranay185417/delight","url":"https://github.com/pranay185417/delight"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2016-finnish","slug":"machine-translation-on-wmt2016-finnish","dataset":"WMT2016 Finnish-English","dataset_url":"/dataset/wmt-2016","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"CT+B/S construction","paper_title":"The University of Sydney's Machine Translation System for WMT19","paper_url":"/paper/the-university-of-sydneys-machine-translation","paper_date":"2019-06-30","arxiv_id":"1907.00494","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2016-russian","slug":"machine-translation-on-wmt2016-russian","dataset":"WMT2016 Russian-English","dataset_url":"/dataset/wmt-2016","rows_in_archive":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper_title":"Edinburgh Neural Machine Translation Systems for WMT 16","paper_url":"/paper/edinburgh-neural-machine-translation-systems","paper_date":"2016-06-09","arxiv_id":"1606.02891","code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/machine-translation-on-wmt2017-english","slug":"machine-translation-on-wmt2017-english","dataset":"WMT2017 English-Finnish","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"OmniNetP","paper_title":"OmniNet: Omnidirectional Representations from Transformers","paper_url":"/paper/omninet-omnidirectional-representations-from","paper_date":"2021-03-01","arxiv_id":"2103.01075","code_links":[{"title":"lucidrains/omninet-pytorch","url":"https://github.com/lucidrains/omninet-pytorch"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2017-english-french","slug":"machine-translation-on-wmt2017-english-french","dataset":"WMT2017 English-French","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"OmniNetP","paper_title":"OmniNet: Omnidirectional Representations from Transformers","paper_url":"/paper/omninet-omnidirectional-representations-from","paper_date":"2021-03-01","arxiv_id":"2103.01075","code_links":[{"title":"lucidrains/omninet-pytorch","url":"https://github.com/lucidrains/omninet-pytorch"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2017-english-german","slug":"machine-translation-on-wmt2017-english-german","dataset":"WMT2017 English-German","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"OmniNetP","paper_title":"OmniNet: Omnidirectional Representations from Transformers","paper_url":"/paper/omninet-omnidirectional-representations-from","paper_date":"2021-03-01","arxiv_id":"2103.01075","code_links":[{"title":"lucidrains/omninet-pytorch","url":"https://github.com/lucidrains/omninet-pytorch"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2017-finnish","slug":"machine-translation-on-wmt2017-finnish","dataset":"WMT2017 Finnish-English","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"CT+B/S construction","paper_title":"The University of Sydney's Machine Translation System for WMT19","paper_url":"/paper/the-university-of-sydneys-machine-translation","paper_date":"2019-06-30","arxiv_id":"1907.00494","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2017-russian","slug":"machine-translation-on-wmt2017-russian","dataset":"WMT2017 Russian-English","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"OmniNetP","paper_title":"OmniNet: Omnidirectional Representations from Transformers","paper_url":"/paper/omninet-omnidirectional-representations-from","paper_date":"2021-03-01","arxiv_id":"2103.01075","code_links":[{"title":"lucidrains/omninet-pytorch","url":"https://github.com/lucidrains/omninet-pytorch"}],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2019-english-1","slug":"machine-translation-on-wmt2019-english-1","dataset":"WMT2019 English-Japanese","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"fiore","paper_title":"Parallel Corpus Filtering via Pre-trained Language Models","paper_url":"/paper/parallel-corpus-filtering-via-pre-trained","paper_date":"2020-05-13","arxiv_id":"2005.06166","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2019-finnish","slug":"machine-translation-on-wmt2019-finnish","dataset":"WMT2019 Finnish-English","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"CT+B/S construction","paper_title":"The University of Sydney's Machine Translation System for WMT19","paper_url":"/paper/the-university-of-sydneys-machine-translation","paper_date":"2019-06-30","arxiv_id":"1907.00494","code_links":[],"syntology":null}},{"leaderboard":"/sota/machine-translation-on-wmt2019-german-english","slug":"machine-translation-on-wmt2019-german-english","dataset":"WMT2019 German-English","dataset_url":null,"rows_in_archive":1,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Exploiting Mono at Scale (single)","paper_title":"Exploiting Monolingual Data at Scale for Neural Machine Translation","paper_url":"/paper/exploiting-monolingual-data-at-scale-for","paper_date":"2019-11-01","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/wmt-2014","name":"WMT 2014","full_name":"","num_papers_in_archive":288},{"url":"/dataset/opensubtitles","name":"OpenSubtitles","full_name":"","num_papers_in_archive":214},{"url":"/dataset/wmt-2016","name":"WMT 2016","full_name":"","num_papers_in_archive":178},{"url":"/dataset/mlqa","name":"MLQA","full_name":"MultiLingual Question Answering","num_papers_in_archive":167},{"url":"/dataset/europarl","name":"Europarl","full_name":"European Parliament Proceedings Parallel Corpus","num_papers_in_archive":128},{"url":"/dataset/flores-200","name":"FLoRes-200","full_name":"","num_papers_in_archive":117},{"url":"/dataset/aspec","name":"ASPEC","full_name":"Asian Scientific Paper Excerpt Corpus","num_papers_in_archive":87},{"url":"/dataset/flores-101","name":"FLoRes-101","full_name":"","num_papers_in_archive":86},{"url":"/dataset/opus-100","name":"OPUS-100","full_name":"","num_papers_in_archive":78},{"url":"/dataset/europarl-st","name":"Europarl-ST","full_name":"","num_papers_in_archive":57},{"url":"/dataset/shifts","name":"Shifts","full_name":"","num_papers_in_archive":55},{"url":"/dataset/mtnt","name":"MTNT","full_name":"","num_papers_in_archive":52},{"url":"/dataset/mkqa","name":"MKQA","full_name":"Multilingual Knowledge Questions and Answers","num_papers_in_archive":49},{"url":"/dataset/samanantar","name":"Samanantar","full_name":"","num_papers_in_archive":40},{"url":"/dataset/tatoeba","name":"Tatoeba","full_name":"Tatoeba","num_papers_in_archive":38},{"url":"/dataset/wmt-2018","name":"WMT 2018","full_name":"","num_papers_in_archive":37},{"url":"/dataset/wmt-2015","name":"WMT 2015","full_name":"","num_papers_in_archive":33},{"url":"/dataset/wmt-2020","name":"WMT 2020","full_name":"","num_papers_in_archive":33},{"url":"/dataset/escape","name":"eSCAPE","full_name":"","num_papers_in_archive":28},{"url":"/dataset/wmt-2016-news","name":"WMT 2016 News","full_name":"WMT 2016 News Translation Task","num_papers_in_archive":24},{"url":"/dataset/coco-cn","name":"COCO-CN","full_name":"","num_papers_in_archive":21},{"url":"/dataset/mlqe-pe","name":"MLQE-PE","full_name":"Multilingual Quality Estimation and Automatic Post-editing Dataset","num_papers_in_archive":20},{"url":"/dataset/paranmt-50m","name":"PARANMT-50M","full_name":"","num_papers_in_archive":13},{"url":"/dataset/duolingo-staple-shared-task","name":"Duolingo STAPLE Shared Task","full_name":"","num_papers_in_archive":10},{"url":"/dataset/xquad-r","name":"LAReQA","full_name":"","num_papers_in_archive":10},{"url":"/dataset/business-scene-dialogue","name":"Business Scene Dialogue","full_name":"","num_papers_in_archive":9},{"url":"/dataset/gigast","name":"GigaST","full_name":"","num_papers_in_archive":8},{"url":"/dataset/nlc2cmd","name":"NLC2CMD","full_name":"","num_papers_in_archive":8},{"url":"/dataset/wmt-2018-news","name":"WMT 2018 News","full_name":"WMT 2018 News Translation Task","num_papers_in_archive":8},{"url":"/dataset/aces","name":"ACES","full_name":"A Translation Accuracy Challenge Set","num_papers_in_archive":7},{"url":"/dataset/demetr","name":"Demetr","full_name":"","num_papers_in_archive":7},{"url":"/dataset/hindi-visual-genome","name":"Hindi Visual Genome","full_name":"","num_papers_in_archive":7},{"url":"/dataset/iwslt-2017","name":"IWSLT 2017","full_name":"","num_papers_in_archive":7},{"url":"/dataset/phomt","name":"PhoMT","full_name":"","num_papers_in_archive":7},{"url":"/dataset/bmeld","name":"BMELD","full_name":"","num_papers_in_archive":6},{"url":"/dataset/iwslt2015","name":"IWSLT2015","full_name":"IWSLT2015","num_papers_in_archive":6},{"url":"/dataset/jparacrawl","name":"JParaCrawl","full_name":"","num_papers_in_archive":6},{"url":"/dataset/shellcode-ia32","name":"Shellcode_IA32","full_name":"Shellcode_IA32","num_papers_in_archive":6},{"url":"/dataset/hindencorp","name":"HindEnCorp","full_name":"","num_papers_in_archive":5},{"url":"/dataset/mlqe","name":"MLQE","full_name":"MultiLingual Quality Estimation","num_papers_in_archive":5},{"url":"/dataset/diabla","name":"DiaBLa","full_name":"","num_papers_in_archive":4},{"url":"/dataset/frmt","name":"FRMT","full_name":"Few-shot Region-aware Machine Translation","num_papers_in_archive":4},{"url":"/dataset/indonlg","name":"IndoNLG","full_name":"","num_papers_in_archive":4},{"url":"/dataset/x-srl","name":"X-SRL","full_name":"","num_papers_in_archive":4},{"url":"/dataset/divemt","name":"DivEMT","full_name":"Post-Editing Effort Across Typologically-diverse Languages","num_papers_in_archive":3},{"url":"/dataset/havg","name":"HaVG","full_name":"Hausa Visual Genome Dataset","num_papers_in_archive":3},{"url":"/dataset/itihasa","name":"Itihasa","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mmid","name":"MMID","full_name":"Massively Multilingual Image Dataset","num_papers_in_archive":3},{"url":"/dataset/textbox-2-0","name":"TextBox 2.0","full_name":"","num_papers_in_archive":3},{"url":"/dataset/amharic-english-parallel-corpus-for-machine","name":"Amharic - English Parallel Corpus for Machine Translation","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ape","name":"APE","full_name":"Automatic Post-Editing","num_papers_in_archive":2},{"url":"/dataset/etymdb-2-0","name":"EtymDB 2.0","full_name":"","num_papers_in_archive":2},{"url":"/dataset/flores-in","name":"Flores-IN","full_name":"Flores-IN","num_papers_in_archive":2},{"url":"/dataset/gatitos","name":"GATITOS","full_name":"Google's Additional Translations Into Tail-languages: Often Short","num_papers_in_archive":2},{"url":"/dataset/muse","name":"MUSE","full_name":"MUSE","num_papers_in_archive":2},{"url":"/dataset/perseus","name":"Perseus","full_name":"","num_papers_in_archive":2},{"url":"/dataset/petci","name":"PETCI","full_name":"PETCI: A Parallel English Translation Dataset of Chinese Idioms","num_papers_in_archive":2},{"url":"/dataset/subedits","name":"SubEdits","full_name":"","num_papers_in_archive":2},{"url":"/dataset/tilde-model-corpus","name":"Tilde MODEL Corpus","full_name":"Tilde Multilingual Open Data for European Languages","num_papers_in_archive":2},{"url":"/dataset/wikicaps","name":"WikiCaps","full_name":"","num_papers_in_archive":2},{"url":"/dataset/alexa-point-of-view","name":"Alexa Point of View","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/bilingual-corpus-of-arabic-english-parallel","name":"Bilingual Corpus of Arabic-English Parallel Tweets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bpersona-chat","name":"BPersona-chat","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bwb","name":"BWB","full_name":"","num_papers_in_archive":1},{"url":"/dataset/congolese-swahili-french-parallel-text","name":"Congolese Swahili – French parallel text corpora","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fgrada","name":"FGraDA","full_name":"Fine-Grained Domain Adaptation Dataset","num_papers_in_archive":1},{"url":"/dataset/humanmt","name":"HumanMT","full_name":"","num_papers_in_archive":1},{"url":"/dataset/igbonlp-datasets","name":"IgboNLP Datasets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kurdishinterdialect","name":"KurdishInterdialect","full_name":"Kurdish parallel corpus in Kurmanji, Sorani and English","num_papers_in_archive":1},{"url":"/dataset/menyo-20k","name":"MENYO-20k","full_name":"","num_papers_in_archive":1},{"url":"/dataset/multi-lingual-bug-reports","name":"Multi Lingual Bug Reports","full_name":"","num_papers_in_archive":1},{"url":"/dataset/phemt","name":"PheMT","full_name":"","num_papers_in_archive":1},{"url":"/dataset/polynewsparallel","name":"PolyNewsParallel","full_name":"","num_papers_in_archive":1},{"url":"/dataset/scb-mt-en-th-2020","name":"scb-mt-en-th-2020","full_name":"","num_papers_in_archive":1},{"url":"/dataset/simpevalasset","name":"SimpEvalASSET","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vashantor-a-large-scale-multilingual","name":"Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wmt-2014-medical","name":"WMT 2014 Medical","full_name":"WMT 2014 Medical Translation Task","num_papers_in_archive":1},{"url":"/dataset/wmt-2015-news","name":"WMT 2015 News","full_name":"WMT 2015 News Translation Task","num_papers_in_archive":1},{"url":"/dataset/wmt-2016-biomedical","name":"WMT 2016 Biomedical","full_name":"WMT 2016 Biomedical Translation Task","num_papers_in_archive":1},{"url":"/dataset/wmt-2016-it","name":"WMT 2016 IT","full_name":"WMT 2016 IT Translation Task","num_papers_in_archive":1},{"url":"/dataset/contracat","name":"ContraCAT","full_name":"Contrastive Coreference Analytical Templates (for Machine Translation)","num_papers_in_archive":0},{"url":"/dataset/wmt-2021-ge-ez-amharic","name":"WMT 2021 Ge'ez-Amharic","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/automatic-post-editing","name":"Automatic Post-Editing"},{"url":"/task/bilingual-lexicon-induction","name":"Bilingual Lexicon Induction"},{"url":"/task/clinical-language-translation","name":"Clinical Language Translation"},{"url":"/task/legal-document-translation","name":"Legal Document Translation"},{"url":"/task/low-resource-neural-machine-translation","name":"Low-Resource Neural Machine Translation"},{"url":"/task/low-resource-neural-machine-translation-2","name":"Low Resource Neural Machine Translation"},{"url":"/task/low-resource-nmt","name":"Low Resource NMT"},{"url":"/task/multimodal-machine-translation","name":"Multimodal Machine Translation"},{"url":"/task/transliteration","name":"Transliteration"},{"url":"/task/unsupervised-machine-translation","name":"Unsupervised Machine Translation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":2444,"tagged_in_all":10752,"items":[{"url":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","repositories_listed":595,"syntology":{"n":946,"n_ran":600,"n_unverified":346,"n_pointer_only":451}},{"url":"/paper/neural-machine-translation-by-jointly","title":"Neural Machine Translation by Jointly Learning to Align and Translate","date":"2014-09-01","arxiv_id":"1409.0473","repositories_listed":124,"syntology":{"n":44,"n_ran":21,"n_unverified":23,"n_pointer_only":16}},{"url":"/paper/sequence-to-sequence-learning-with-neural","title":"Sequence to Sequence Learning with Neural Networks","date":"2014-09-10","arxiv_id":"1409.3215","repositories_listed":74,"syntology":{"n":25,"n_ran":11,"n_unverified":14,"n_pointer_only":9}},{"url":"/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","arxiv_id":"1910.10683","repositories_listed":57,"syntology":{"n":31,"n_ran":2,"n_unverified":29,"n_pointer_only":0}},{"url":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","repositories_listed":47,"syntology":{"n":53,"n_ran":22,"n_unverified":31,"n_pointer_only":7}},{"url":"/paper/effective-approaches-to-attention-based","title":"Effective Approaches to Attention-based Neural Machine Translation","date":"2015-08-17","arxiv_id":"1508.04025","repositories_listed":44,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/learning-phrase-representations-using-rnn","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","date":"2014-06-03","arxiv_id":"1406.1078","repositories_listed":42,"syntology":{"n":22,"n_ran":10,"n_unverified":12,"n_pointer_only":14}},{"url":"/paper/convolutional-sequence-to-sequence-learning","title":"Convolutional Sequence to Sequence Learning","date":"2017-05-08","arxiv_id":"1705.03122","repositories_listed":37,"syntology":null},{"url":"/paper/an-empirical-evaluation-of-generic","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","date":"2018-03-04","arxiv_id":"1803.01271","repositories_listed":35,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/googles-neural-machine-translation-system","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","date":"2016-09-26","arxiv_id":"1609.08144","repositories_listed":28,"syntology":{"n":46,"n_ran":23,"n_unverified":23,"n_pointer_only":12}},{"url":"/paper/3d-u-net-learning-dense-volumetric","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","date":"2016-06-21","arxiv_id":"1606.06650","repositories_listed":27,"syntology":{"n":76,"n_ran":53,"n_unverified":23,"n_pointer_only":20}},{"url":"/paper/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","date":"2015-08-31","arxiv_id":"1508.07909","repositories_listed":26,"syntology":{"n":30,"n_ran":21,"n_unverified":9,"n_pointer_only":21}},{"url":"/paper/diverse-beam-search-decoding-diverse","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","date":"2016-10-07","arxiv_id":"1610.02424","repositories_listed":25,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/on-the-variance-of-the-adaptive-learning-rate","title":"On the Variance of the Adaptive Learning Rate and Beyond","date":"2019-08-08","arxiv_id":"1908.03265","repositories_listed":21,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/recurrent-neural-network-regularization","title":"Recurrent Neural Network Regularization","date":"2014-09-08","arxiv_id":"1409.2329","repositories_listed":21,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/bertscore-evaluating-text-generation-with","title":"BERTScore: Evaluating Text Generation with BERT","date":"2019-04-21","arxiv_id":"1904.09675","repositories_listed":20,"syntology":{"n":76,"n_ran":44,"n_unverified":32,"n_pointer_only":33}},{"url":"/paper/word-translation-without-parallel-data","title":"Word Translation Without Parallel Data","date":"2017-10-11","arxiv_id":"1710.04087","repositories_listed":20,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":8}},{"url":"/paper/resmlp-feedforward-networks-for-image","title":"ResMLP: Feedforward networks for image classification with data-efficient training","date":"2021-05-07","arxiv_id":"2105.03404","repositories_listed":19,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/lookahead-optimizer-k-steps-forward-1-step","title":"Lookahead Optimizer: k steps forward, 1 step back","date":"2019-07-19","arxiv_id":"1907.08610","repositories_listed":19,"syntology":null},{"url":"/paper/cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","repositories_listed":17,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/sockeye-a-toolkit-for-neural-machine","title":"Sockeye: A Toolkit for Neural Machine Translation","date":"2017-12-15","arxiv_id":"1712.05690","repositories_listed":16,"syntology":null},{"url":"/paper/qanet-combining-local-convolution-with-global","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","date":"2018-04-23","arxiv_id":"1804.09541","repositories_listed":15,"syntology":{"n":19,"n_ran":7,"n_unverified":12,"n_pointer_only":2}},{"url":"/paper/tensor2tensor-for-neural-machine-translation","title":"Tensor2Tensor for Neural Machine Translation","date":"2018-03-16","arxiv_id":"1803.07416","repositories_listed":15,"syntology":{"n":48,"n_ran":1,"n_unverified":47,"n_pointer_only":0}},{"url":"/paper/phrase-based-neural-unsupervised-machine","title":"Phrase-Based & Neural Unsupervised Machine Translation","date":"2018-04-20","arxiv_id":"1804.07755","repositories_listed":14,"syntology":null},{"url":"/paper/unsupervised-machine-translation-using","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","date":"2017-10-31","arxiv_id":"1711.00043","repositories_listed":14,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":5}},{"url":"/paper/attention-based-models-for-speech-recognition","title":"Attention-Based Models for Speech Recognition","date":"2015-06-24","arxiv_id":"1506.07503","repositories_listed":14,"syntology":null},{"url":"/paper/gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","repositories_listed":13,"syntology":{"n":25,"n_ran":1,"n_unverified":24,"n_pointer_only":16}},{"url":"/paper/self-attention-with-relative-position","title":"Self-Attention with Relative Position Representations","date":"2018-03-06","arxiv_id":"1803.02155","repositories_listed":13,"syntology":{"n":23,"n_ran":13,"n_unverified":10,"n_pointer_only":3}},{"url":"/paper/fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","repositories_listed":12,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":24,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}