{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":33,"of":33,"counts":{"papers_with_a_benchmark_row":33,"with_a_code_link":26,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":33,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/gentranslate-large-language-models-are","slug":"gentranslate-large-language-models-are","title":"GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators","date":"2024-02-10","arxiv_id":"2402.06894","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textbox-2-0-a-text-generation-library-with","slug":"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","arxiv_id":"2212.13005","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}}}},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":8,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/language-models-not-just-for-pre-training","slug":"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","arxiv_id":"2011.07164","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/incorporating-a-local-translation-mechanism","slug":"incorporating-a-local-translation-mechanism","title":"Incorporating a Local Translation Mechanism into Non-autoregressive Translation","date":"2020-11-12","arxiv_id":"2011.06132","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["shawnkx/NAT-with-Local-AT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/incorporating-a-local-translation-mechanism#ran","syntology_url":"https://syntology.ai/paper/2011.06132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06132"}}}},{"paper":"/paper/alleviating-the-inequality-of-attention-heads","slug":"alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2020-09-21","arxiv_id":"2009.09672","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/delight-very-deep-and-light-weight","slug":"delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","arxiv_id":"2008.00623","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["sacmehta/delight"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/delight-very-deep-and-light-weight#ran","syntology_url":"https://syntology.ai/paper/2008.00623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00623"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":4,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/incorporating-bert-into-neural-machine-1","slug":"incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","arxiv_id":"2002.06823","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/exploiting-monolingual-data-at-scale-for","slug":"exploiting-monolingual-data-at-scale-for","title":"Exploiting Monolingual Data at Scale for Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/on-the-adequacy-of-untuned-warmup-for#ran","syntology_url":"https://syntology.ai/paper/1910.04209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04209"}}}},{"paper":"/paper/flowseq-non-autoregressive-conditional","slug":"flowseq-non-autoregressive-conditional","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","date":"2019-09-05","arxiv_id":"1909.02480","rows_on_this_dataset":10,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["XuezheMax/flowseq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flowseq-non-autoregressive-conditional#ran","syntology_url":"https://syntology.ai/paper/1909.02480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02480"}}}},{"paper":"/paper/adaptively-sparse-transformers","slug":"adaptively-sparse-transformers","title":"Adaptively Sparse Transformers","date":"2019-08-30","arxiv_id":"1909.00015","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["deep-spin/entmax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/adaptively-sparse-transformers#ran","syntology_url":"https://syntology.ai/paper/1909.00015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00015"}}}},{"paper":"/paper/the-university-of-sydneys-machine-translation","slug":"the-university-of-sydneys-machine-translation","title":"The University of Sydney's Machine Translation System for WMT19","date":"2019-06-30","arxiv_id":"1907.00494","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/levenshtein-transformer","slug":"levenshtein-transformer","title":"Levenshtein Transformer","date":"2019-05-27","arxiv_id":"1905.11006","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/mass-masked-sequence-to-sequence-pre-training","slug":"mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","arxiv_id":"1905.02450","rows_on_this_dataset":4,"code_links":7,"syntology":null},{"paper":"/paper/multi-agent-dual-learning","slug":"multi-agent-dual-learning","title":"Multi-Agent Dual Learning","date":"2019-05-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/an-effective-approach-to-unsupervised-machine","slug":"an-effective-approach-to-unsupervised-machine","title":"An Effective Approach to Unsupervised Machine Translation","date":"2019-02-04","arxiv_id":"1902.01313","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","rows_on_this_dataset":6,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-lingual-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/1901.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07291"}}}},{"paper":"/paper/unsupervised-neural-machine-translation-with","slug":"unsupervised-neural-machine-translation-with","title":"Unsupervised Neural Machine Translation with SMT as Posterior Regularization","date":"2019-01-14","arxiv_id":"1901.04112","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["Imagist-Shuo/UNMT-SPR"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-neural-machine-translation-with#ran","syntology_url":"https://syntology.ai/paper/1901.04112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.04112"}}}},{"paper":"/paper/unsupervised-neural-machine-translation-1","slug":"unsupervised-neural-machine-translation-1","title":"Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation","date":"2018-10-30","arxiv_id":"1810.12703","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-statistical-machine-translation","slug":"unsupervised-statistical-machine-translation","title":"Unsupervised Statistical Machine Translation","date":"2018-09-04","arxiv_id":"1809.01272","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/unsupervised-neural-machine-translation-with-1","slug":"unsupervised-neural-machine-translation-with-1","title":"Unsupervised Neural Machine Translation with Weight Sharing","date":"2018-04-24","arxiv_id":"1804.09057","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/exploiting-semantics-in-neural-machine","slug":"exploiting-semantics-in-neural-machine","title":"Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks","date":"2018-04-23","arxiv_id":"1804.08313","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/phrase-based-neural-unsupervised-machine","slug":"phrase-based-neural-unsupervised-machine","title":"Phrase-Based & Neural Unsupervised Machine Translation","date":"2018-04-20","arxiv_id":"1804.07755","rows_on_this_dataset":8,"code_links":14,"syntology":null},{"paper":"/paper/deterministic-non-autoregressive-neural","slug":"deterministic-non-autoregressive-neural","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","date":"2018-02-19","arxiv_id":"1802.06901","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["nyu-dl/dl4mt-nonauto"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deterministic-non-autoregressive-neural#ran","syntology_url":"https://syntology.ai/paper/1802.06901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06901"}}}},{"paper":"/paper/non-autoregressive-neural-machine-translation-1","slug":"non-autoregressive-neural-machine-translation-1","title":"Non-Autoregressive Neural Machine Translation","date":"2017-11-07","arxiv_id":"1711.02281","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["salesforce/nonauto-nmt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-autoregressive-neural-machine-translation-1#ran","syntology_url":"https://syntology.ai/paper/1711.02281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.02281"}}}},{"paper":"/paper/unsupervised-machine-translation-using","slug":"unsupervised-machine-translation-using","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","date":"2017-10-31","arxiv_id":"1711.00043","rows_on_this_dataset":2,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-machine-translation-using#ran","syntology_url":"https://syntology.ai/paper/1711.00043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00043"}}}},{"paper":"/paper/convolutional-sequence-to-sequence-learning","slug":"convolutional-sequence-to-sequence-learning","title":"Convolutional Sequence to Sequence Learning","date":"2017-05-08","arxiv_id":"1705.03122","rows_on_this_dataset":1,"code_links":37,"syntology":null},{"paper":"/paper/a-convolutional-encoder-model-for-neural","slug":"a-convolutional-encoder-model-for-neural","title":"A Convolutional Encoder Model for Neural Machine Translation","date":"2016-11-07","arxiv_id":"1611.02344","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/the-qt21himl-combined-machine-translation","slug":"the-qt21himl-combined-machine-translation","title":"The QT21/HimL Combined Machine Translation System","date":"2016-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/edinburgh-neural-machine-translation-systems","slug":"edinburgh-neural-machine-translation-systems","title":"Edinburgh Neural Machine Translation Systems for WMT 16","date":"2016-06-09","arxiv_id":"1606.02891","rows_on_this_dataset":8,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["rsennrich/wmt16-scripts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/edinburgh-neural-machine-translation-systems#ran","syntology_url":"https://syntology.ai/paper/1606.02891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02891"}}}},{"paper":"/paper/linguistic-input-features-improve-neural","slug":"linguistic-input-features-improve-neural","title":"Linguistic Input Features Improve Neural Machine Translation","date":"2016-06-09","arxiv_id":"1606.02892","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/gentranslate-large-language-models-are","slug":"gentranslate-large-language-models-are","title":"GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators","date":"2024-02-10","arxiv_id":"2402.06894","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textbox-2-0-a-text-generation-library-with","slug":"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","arxiv_id":"2212.13005","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}}}},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":8,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/language-models-not-just-for-pre-training","slug":"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","arxiv_id":"2011.07164","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/incorporating-a-local-translation-mechanism","slug":"incorporating-a-local-translation-mechanism","title":"Incorporating a Local Translation Mechanism into Non-autoregressive Translation","date":"2020-11-12","arxiv_id":"2011.06132","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["shawnkx/NAT-with-Local-AT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/incorporating-a-local-translation-mechanism#ran","syntology_url":"https://syntology.ai/paper/2011.06132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06132"}}}},{"paper":"/paper/alleviating-the-inequality-of-attention-heads","slug":"alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2020-09-21","arxiv_id":"2009.09672","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/delight-very-deep-and-light-weight","slug":"delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","arxiv_id":"2008.00623","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["sacmehta/delight"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/delight-very-deep-and-light-weight#ran","syntology_url":"https://syntology.ai/paper/2008.00623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00623"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":4,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/incorporating-bert-into-neural-machine-1","slug":"incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","arxiv_id":"2002.06823","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/exploiting-monolingual-data-at-scale-for","slug":"exploiting-monolingual-data-at-scale-for","title":"Exploiting Monolingual Data at Scale for Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/on-the-adequacy-of-untuned-warmup-for#ran","syntology_url":"https://syntology.ai/paper/1910.04209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04209"}}}},{"paper":"/paper/flowseq-non-autoregressive-conditional","slug":"flowseq-non-autoregressive-conditional","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","date":"2019-09-05","arxiv_id":"1909.02480","rows_on_this_dataset":10,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["XuezheMax/flowseq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flowseq-non-autoregressive-conditional#ran","syntology_url":"https://syntology.ai/paper/1909.02480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02480"}}}},{"paper":"/paper/adaptively-sparse-transformers","slug":"adaptively-sparse-transformers","title":"Adaptively Sparse Transformers","date":"2019-08-30","arxiv_id":"1909.00015","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["deep-spin/entmax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/adaptively-sparse-transformers#ran","syntology_url":"https://syntology.ai/paper/1909.00015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00015"}}}},{"paper":"/paper/the-university-of-sydneys-machine-translation","slug":"the-university-of-sydneys-machine-translation","title":"The University of Sydney's Machine Translation System for WMT19","date":"2019-06-30","arxiv_id":"1907.00494","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/levenshtein-transformer","slug":"levenshtein-transformer","title":"Levenshtein Transformer","date":"2019-05-27","arxiv_id":"1905.11006","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/mass-masked-sequence-to-sequence-pre-training","slug":"mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","arxiv_id":"1905.02450","rows_on_this_dataset":4,"code_links":7,"syntology":null},{"paper":"/paper/multi-agent-dual-learning","slug":"multi-agent-dual-learning","title":"Multi-Agent Dual Learning","date":"2019-05-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/an-effective-approach-to-unsupervised-machine","slug":"an-effective-approach-to-unsupervised-machine","title":"An Effective Approach to Unsupervised Machine Translation","date":"2019-02-04","arxiv_id":"1902.01313","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","rows_on_this_dataset":6,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-lingual-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/1901.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07291"}}}},{"paper":"/paper/unsupervised-neural-machine-translation-with","slug":"unsupervised-neural-machine-translation-with","title":"Unsupervised Neural Machine Translation with SMT as Posterior Regularization","date":"2019-01-14","arxiv_id":"1901.04112","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["Imagist-Shuo/UNMT-SPR"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-neural-machine-translation-with#ran","syntology_url":"https://syntology.ai/paper/1901.04112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.04112"}}}},{"paper":"/paper/unsupervised-neural-machine-translation-1","slug":"unsupervised-neural-machine-translation-1","title":"Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation","date":"2018-10-30","arxiv_id":"1810.12703","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-statistical-machine-translation","slug":"unsupervised-statistical-machine-translation","title":"Unsupervised Statistical Machine Translation","date":"2018-09-04","arxiv_id":"1809.01272","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/unsupervised-neural-machine-translation-with-1","slug":"unsupervised-neural-machine-translation-with-1","title":"Unsupervised Neural Machine Translation with Weight Sharing","date":"2018-04-24","arxiv_id":"1804.09057","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/exploiting-semantics-in-neural-machine","slug":"exploiting-semantics-in-neural-machine","title":"Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks","date":"2018-04-23","arxiv_id":"1804.08313","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/phrase-based-neural-unsupervised-machine","slug":"phrase-based-neural-unsupervised-machine","title":"Phrase-Based & Neural Unsupervised Machine Translation","date":"2018-04-20","arxiv_id":"1804.07755","rows_on_this_dataset":8,"code_links":14,"syntology":null},{"paper":"/paper/deterministic-non-autoregressive-neural","slug":"deterministic-non-autoregressive-neural","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","date":"2018-02-19","arxiv_id":"1802.06901","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["nyu-dl/dl4mt-nonauto"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deterministic-non-autoregressive-neural#ran","syntology_url":"https://syntology.ai/paper/1802.06901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06901"}}}},{"paper":"/paper/non-autoregressive-neural-machine-translation-1","slug":"non-autoregressive-neural-machine-translation-1","title":"Non-Autoregressive Neural Machine Translation","date":"2017-11-07","arxiv_id":"1711.02281","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["salesforce/nonauto-nmt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-autoregressive-neural-machine-translation-1#ran","syntology_url":"https://syntology.ai/paper/1711.02281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.02281"}}}},{"paper":"/paper/unsupervised-machine-translation-using","slug":"unsupervised-machine-translation-using","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","date":"2017-10-31","arxiv_id":"1711.00043","rows_on_this_dataset":2,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-machine-translation-using#ran","syntology_url":"https://syntology.ai/paper/1711.00043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00043"}}}},{"paper":"/paper/convolutional-sequence-to-sequence-learning","slug":"convolutional-sequence-to-sequence-learning","title":"Convolutional Sequence to Sequence Learning","date":"2017-05-08","arxiv_id":"1705.03122","rows_on_this_dataset":1,"code_links":37,"syntology":null},{"paper":"/paper/a-convolutional-encoder-model-for-neural","slug":"a-convolutional-encoder-model-for-neural","title":"A Convolutional Encoder Model for Neural Machine Translation","date":"2016-11-07","arxiv_id":"1611.02344","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/the-qt21himl-combined-machine-translation","slug":"the-qt21himl-combined-machine-translation","title":"The QT21/HimL Combined Machine Translation System","date":"2016-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/edinburgh-neural-machine-translation-systems","slug":"edinburgh-neural-machine-translation-systems","title":"Edinburgh Neural Machine Translation Systems for WMT 16","date":"2016-06-09","arxiv_id":"1606.02891","rows_on_this_dataset":8,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["rsennrich/wmt16-scripts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/edinburgh-neural-machine-translation-systems#ran","syntology_url":"https://syntology.ai/paper/1606.02891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02891"}}}},{"paper":"/paper/linguistic-input-features-improve-neural","slug":"linguistic-input-features-improve-neural","title":"Linguistic Input Features Improve Neural Machine Translation","date":"2016-06-09","arxiv_id":"1606.02892","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/dataset/wmt-2016/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/wmt-2016/papers/ran/1","json":"/dataset/wmt-2016/papers/ran/1.json","rows":13}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":14,"samples_harvested":127,"samples_ran":86,"samples_constructed":3,"samples_ran_checked":66,"samples_ran_instrument_failed":20,"samples_unverified":41,"pointer_only_for_licence":15,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":13,"papers_with_a_run_with_no_instrument_failure":10,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"4849a56c9f569dfcea1c4acddc0a535a4419bab42824ea29fe602f7852e70612","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}