{"url":"/dataset/wmt-2016","name":"WMT 2016","full_name":null,"description_markdown":"**WMT 2016** is a collection of datasets used in shared tasks of the First Conference on Machine Translation. The conference builds on ten previous Workshops on statistical Machine Translation.\r\n\r\nThe conference featured ten shared tasks:\r\n\r\n- a news translation task,\r\n- an IT domain translation task,\r\n- a biomedical translation task,\r\n- an automatic post-editing task,\r\n- a metrics task (assess MT quality given reference translation).\r\n- a quality estimation task (assess MT quality without access to any reference),\r\n- a tuning task (optimize a given MT system),\r\n- a pronoun translation task,\r\n- a bilingual document alignment task,\r\n- a multimodal translation task.\r\n\r\nSource: [http://www.statmt.org/wmt16/index.html](http://www.statmt.org/wmt16/index.html)","description_withheld":null,"homepage":"http://www.statmt.org/wmt16/index.html","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/findings-of-the-2016-conference-on-machine","title":"Findings of the 2016 Conference on Machine Translation","first_author":"Ond{\\v{r}}ej Bojar","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Translation deu-eng","url":"/task/translation-deu-eng","datasets_with_task":"/datasets/task/translation-deu-eng"},{"name":"Binary Classification","url":"/task/binary-classification","datasets_with_task":"/datasets/task/binary-classification"},{"name":"Translation eng-deu","url":"/task/translation-eng-deu","datasets_with_task":"/datasets/task/translation-eng-deu"},{"name":"Sequence-to-sequence Language Modeling","url":"/task/sequence-to-sequence-language-modeling","datasets_with_task":"/datasets/task/sequence-to-sequence-language-modeling"},{"name":"Unsupervised Machine Translation","url":"/task/unsupervised-machine-translation","datasets_with_task":"/datasets/task/unsupervised-machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"German","url":"/datasets/language/german"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Czech","url":"/datasets/language/czech"},{"name":"Finnish","url":"/datasets/language/finnish"},{"name":"Romanian","url":"/datasets/language/romanian"}],"variants":["wmt16 ro-en","newstest2016-ende eng-deu","newstest2016-deen deu-eng","newstest2016-ende","newstest2016-deen","wmt16","WMT2016 En-Ro","WMT 2016","WMT2016 Russian-English","WMT2016 Finnish-English","WMT2016 English-Russian","WMT2016 English-French","WMT2016 English-Czech","WMT2016 Czech-English","WMT2016 Romanian-English","WMT2016 German-English","WMT2016 English-Romanian","WMT2016 English-German","WMT2016 English--Romanian"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wmt/wmt16","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wmt16","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wmt16_translate","frameworks":["tf","jax"]}],"num_papers_in_archive":178,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset_variant":"WMT2016 English-Romanian","rows":21,"metrics":["BLEU score","BLEU-4"],"first_row_in_archive_order":{"model":"DeLighT","paper":"/paper/delight-very-deep-and-light-weight","metrics":{"BLEU score":"34.7"},"code_links":[{"title":"sacmehta/delight","url":"https://github.com/sacmehta/delight"},{"title":"pranay185417/delight","url":"https://github.com/pranay185417/delight"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset_variant":"WMT2016 Romanian-English","rows":21,"metrics":["BLEU score","BLEU-4"],"first_row_in_archive_order":{"model":"fast-noisy-channel-modeling","paper":"/paper/language-models-not-just-for-pre-training","metrics":{"BLEU score":"40.3"},"code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/fast_noisy_channel"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-german","task":"Machine Translation","dataset_variant":"WMT2016 English-German","rows":12,"metrics":["BLEU score","SacreBLEU"],"first_row_in_archive_order":{"model":"MADL","paper":"/paper/multi-agent-dual-learning","metrics":{"BLEU score":"40.68"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-german-english","task":"Machine Translation","dataset_variant":"WMT2016 German-English","rows":8,"metrics":["BLEU score","SacreBLEU"],"first_row_in_archive_order":{"model":"FLAN 137B (few-shot, k=11)","paper":"/paper/finetuned-language-models-are-zero-shot","metrics":{"BLEU score":"40.7"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016","task":"Unsupervised Machine Translation","dataset_variant":"WMT2016 English-German","rows":7,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"GPT-3 175B (Few-Shot)","paper":"/paper/language-models-are-few-shot-learners","metrics":{"BLEU":"29.7"},"code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-1","task":"Unsupervised Machine Translation","dataset_variant":"WMT2016 German-English","rows":7,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"GPT-3 175B (Few-Shot)","paper":"/paper/language-models-are-few-shot-learners","metrics":{"BLEU":"40.6"},"code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-english","task":"Machine Translation","dataset_variant":"WMT2016 English-Russian","rows":4,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper":"/paper/edinburgh-neural-machine-translation-systems","metrics":{"BLEU score":"26.0"},"code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-2","task":"Unsupervised Machine Translation","dataset_variant":"WMT2016 English-Romanian","rows":3,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"GPT-3 175B (Few-Shot)","paper":"/paper/language-models-are-few-shot-learners","metrics":{"BLEU":"21"},"code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-3","task":"Unsupervised Machine Translation","dataset_variant":"WMT2016 Romanian-English","rows":3,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"GPT-3 175B (Few-Shot)","paper":"/paper/language-models-are-few-shot-learners","metrics":{"BLEU":"39.5"},"code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-5","task":"Unsupervised Machine Translation","dataset_variant":"WMT2016 English--Romanian","rows":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"BERT-fused NMT","paper":"/paper/incorporating-bert-into-neural-machine-1","metrics":{"BLEU":"36.02"},"code_links":[{"title":"bert-nmt/bert-nmt","url":"https://github.com/bert-nmt/bert-nmt"},{"title":"vivekgohel56/Neural-machine-translation-english-to-polish","url":"https://github.com/vivekgohel56/Neural-machine-translation-english-to-polish"},{"title":"StuartCHAN/KARL","url":"https://github.com/StuartCHAN/KARL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-czech-english","task":"Machine Translation","dataset_variant":"WMT2016 Czech-English","rows":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper":"/paper/edinburgh-neural-machine-translation-systems","metrics":{"BLEU score":"31.4"},"code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-czech","task":"Machine Translation","dataset_variant":"WMT2016 English-Czech","rows":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper":"/paper/edinburgh-neural-machine-translation-systems","metrics":{"BLEU score":"25.8"},"code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-french","task":"Machine Translation","dataset_variant":"WMT2016 English-French","rows":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"DeLighT","paper":"/paper/delight-very-deep-and-light-weight","metrics":{"BLEU score":"40.5"},"code_links":[{"title":"sacmehta/delight","url":"https://github.com/sacmehta/delight"},{"title":"pranay185417/delight","url":"https://github.com/pranay185417/delight"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-finnish","task":"Machine Translation","dataset_variant":"WMT2016 Finnish-English","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"CT+B/S construction","paper":"/paper/the-university-of-sydneys-machine-translation","metrics":{"BLEU":"32.4"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt2016-russian","task":"Machine Translation","dataset_variant":"WMT2016 Russian-English","rows":1,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"Attentional encoder-decoder + BPE","paper":"/paper/edinburgh-neural-machine-translation-systems","metrics":{"BLEU score":"28.0"},"code_links":[{"title":"rsennrich/wmt16-scripts","url":"https://github.com/rsennrich/wmt16-scripts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/binary-classification-on-wmt16","task":"Binary Classification","dataset_variant":"wmt16","rows":0,"metrics":["Cosine Accuracy","Cosine Accuracy Threshold","Cosine Ap","Cosine F1","Cosine F1 Threshold","Cosine Mcc","Cosine Precision","Cosine Recall"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gentranslate-large-language-models-are","title":"GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators","date":"2024-02-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","rows_on_this_dataset":8,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-models-not-just-for-pre-training","title":"Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling","date":"2020-11-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/incorporating-a-local-translation-mechanism","title":"Incorporating a Local Translation Mechanism into Non-autoregressive Translation","date":"2020-11-12","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2020-09-21","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","rows_on_this_dataset":4,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":65,"samples_ran":15,"samples_unverified":50,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/exploiting-monolingual-data-at-scale-for","title":"Exploiting Monolingual Data at Scale for Neural Machine Translation","date":"2019-11-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/flowseq-non-autoregressive-conditional","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","date":"2019-09-05","rows_on_this_dataset":10,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptively-sparse-transformers","title":"Adaptively Sparse Transformers","date":"2019-08-30","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-university-of-sydneys-machine-translation","title":"The University of Sydney's Machine Translation System for WMT19","date":"2019-06-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/levenshtein-transformer","title":"Levenshtein Transformer","date":"2019-05-27","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","rows_on_this_dataset":4,"code_links":7,"syntology":null},{"paper":"/paper/multi-agent-dual-learning","title":"Multi-Agent Dual Learning","date":"2019-05-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/an-effective-approach-to-unsupervised-machine","title":"An Effective Approach to Unsupervised Machine Translation","date":"2019-02-04","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","rows_on_this_dataset":6,"code_links":17,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-neural-machine-translation-with","title":"Unsupervised Neural Machine Translation with SMT as Posterior Regularization","date":"2019-01-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":0,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-neural-machine-translation-1","title":"Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation","date":"2018-10-30","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-statistical-machine-translation","title":"Unsupervised Statistical Machine Translation","date":"2018-09-04","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/unsupervised-neural-machine-translation-with-1","title":"Unsupervised Neural Machine Translation with Weight Sharing","date":"2018-04-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/exploiting-semantics-in-neural-machine","title":"Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks","date":"2018-04-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/phrase-based-neural-unsupervised-machine","title":"Phrase-Based & Neural Unsupervised Machine Translation","date":"2018-04-20","rows_on_this_dataset":8,"code_links":14,"syntology":null},{"paper":"/paper/deterministic-non-autoregressive-neural","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","date":"2018-02-19","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/non-autoregressive-neural-machine-translation-1","title":"Non-Autoregressive Neural Machine Translation","date":"2017-11-07","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-machine-translation-using","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","date":"2017-10-31","rows_on_this_dataset":2,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":3,"samples_unverified":11,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/convolutional-sequence-to-sequence-learning","title":"Convolutional Sequence to Sequence Learning","date":"2017-05-08","rows_on_this_dataset":1,"code_links":37,"syntology":null},{"paper":"/paper/a-convolutional-encoder-model-for-neural","title":"A Convolutional Encoder Model for Neural Machine Translation","date":"2016-11-07","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/the-qt21himl-combined-machine-translation","title":"The QT21/HimL Combined Machine Translation System","date":"2016-08-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/linguistic-input-features-improve-neural","title":"Linguistic Input Features Improve Neural Machine Translation","date":"2016-06-09","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/edinburgh-neural-machine-translation-systems","title":"Edinburgh Neural Machine Translation Systems for WMT 16","date":"2016-06-09","rows_on_this_dataset":8,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":14,"samples_harvested":127,"samples_ran":34,"samples_unverified":93,"pointer_only_for_licence":12,"papers_with_no_sample_that_ran":4,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}