{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","arxiv_id":"2010.11934","date":"2020-10-22","proceeding":"NAACL 2021 4","authors":["Linting Xue","Noah Constant","Adam Roberts","Mihir Kale","Rami Al-Rfou","Aditya Siddhant","Aditya Barua","Colin Raffel"],"abstract":"The recent \"Text-to-Text Transfer Transformer\" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent \"accidental translation\" in the zero-shot setting, where a generative model chooses to (partially) translate its prediction into the wrong language. All of the code and model checkpoints used in this work are publicly available.","url_abs":"https://arxiv.org/abs/2010.11934v3","url_pdf":"https://arxiv.org/pdf/2010.11934v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/google-research/multilingual-t5","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/KoshiroSato/Flask_NLP_App","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/KoshiroSato/Simple_Transformers_mT5_finetuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/MorenoLaQuatra/bart-it","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/google-research/byt5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/manshri/tesum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mt5-a-massively-multilingual-pre-trained-text","repo_url":"https://github.com/pwc-1/Paper-5/tree/main/mt5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"},{"method_slug":"mt5","method_name":"mT5"}],"datasets_introduced":[{"slug":"mc4","name":"mC4","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-parus","task":"Common Sense Reasoning","dataset":"PARus","model":"MT5 Large","rank_in_archive_order":14,"of":22,"metrics":{"Accuracy":"0.504"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-rwsd","task":"Common Sense Reasoning","dataset":"RWSD","model":"MT5 Large","rank_in_archive_order":13,"of":22,"metrics":{"Accuracy":"0.669"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-rucos","task":"Common Sense Reasoning","dataset":"RuCoS","model":"MT5 Large","rank_in_archive_order":10,"of":22,"metrics":{"Average F1":"0.57","EM ":"0.562"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-lidirus","task":"Natural Language Inference","dataset":"LiDiRus","model":"MT5 Large","rank_in_archive_order":16,"of":22,"metrics":{"MCC":"0.061"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rcb","task":"Natural Language Inference","dataset":"RCB","model":"MT5 Large","rank_in_archive_order":11,"of":22,"metrics":{"Accuracy":"0.454","Average F1":"0.366"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-terra","task":"Natural Language Inference","dataset":"TERRa","model":"MT5 Large","rank_in_archive_order":16,"of":22,"metrics":{"Accuracy":"0.561"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-danetqa","task":"Question Answering","dataset":"DaNetQA","model":"MT5 Large","rank_in_archive_order":10,"of":22,"metrics":{"Accuracy":"0.657"},"uses_additional_data":false},{"leaderboard":"/sota/reading-comprehension-on-muserc","task":"Reading Comprehension","dataset":"MuSeRC","model":"MT5 Large","rank_in_archive_order":2,"of":22,"metrics":{"Average F1":"0.844","EM ":"0.543"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-lingual-transfer-on-xtreme","task":"Zero-Shot Cross-Lingual Transfer","dataset":"XTREME","model":"mT5","rank_in_archive_order":23,"of":25,"metrics":{"Avg":"40.9","Question Answering":"73.6","Sentence Retrieval":"NA","Sentence-pair Classification":"89.8","Structured Prediction":"NA"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.11934","atlas_url":"https://app.syntology.ai/?focus=2010.11934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11934"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KoshiroSato/Flask_NLP_App","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MorenoLaQuatra/bart-it","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manshri/tesum","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KoshiroSato/Simple_Transformers_mT5_finetuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/multilingual-t5","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-5/tree/main/mt5","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/byt5","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":8},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":8,"ran":5,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ab4db4a59f94ef40","entry":"bert_predict","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/bert_model.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/bert_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab4db4a59f94ef40"}},{"code_sha256_prefix":"0d9ef0d0dfe26859","entry":"mt5_post_processing","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/mt5_model.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/mt5_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d9ef0d0dfe26859"}},{"code_sha256_prefix":"0d4436476da0cc30","entry":"predict_with_post_processing","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/bert_model.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/bert_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d4436476da0cc30"}},{"code_sha256_prefix":"2641f706223d1e5c","entry":"preprocess_logits_for_metrics","repo":"MorenoLaQuatra/bart-it","repo_kind":"listed","path":"summarization/finetune_summarization.py","file_url":"https://github.com/MorenoLaQuatra/bart-it/blob/HEAD/summarization/finetune_summarization.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2641f706223d1e5c"}},{"code_sha256_prefix":"e445d0574fe31243","entry":"read_txt","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/utils.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e445d0574fe31243"}},{"code_sha256_prefix":"d10b1ac136fbfec1","entry":"app_logger","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/logger.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d10b1ac136fbfec1"}},{"code_sha256_prefix":"baf8e460eed595db","entry":"model_io_logger","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/logger.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baf8e460eed595db"}},{"code_sha256_prefix":"4ad4262f32bec052","entry":"normalize_mlqa","repo":"google-research/multilingual-t5","repo_kind":"official","path":"multilingual_t5/evaluation/metrics.py","file_url":"https://github.com/google-research/multilingual-t5/blob/HEAD/multilingual_t5/evaluation/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ad4262f32bec052"}},{"code_sha256_prefix":"c9737e28fdfdcfe9","entry":"read_yaml","repo":"KoshiroSato/Flask_NLP_App","repo_kind":"listed","path":"flask/flaskapp/lib/utils.py","file_url":"https://github.com/KoshiroSato/Flask_NLP_App/blob/HEAD/flask/flaskapp/lib/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9737e28fdfdcfe9"}},{"code_sha256_prefix":"3a70b94fccf1c165","entry":"span_f1","repo":"google-research/multilingual-t5","repo_kind":"official","path":"multilingual_t5/evaluation/metrics.py","file_url":"https://github.com/google-research/multilingual-t5/blob/HEAD/multilingual_t5/evaluation/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3a70b94fccf1c165"}},{"code_sha256_prefix":"6a5b181d28b784b6","entry":"wikiann","repo":"google-research/multilingual-t5","repo_kind":"official","path":"multilingual_t5/preprocessors.py","file_url":"https://github.com/google-research/multilingual-t5/blob/HEAD/multilingual_t5/preprocessors.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a5b181d28b784b6"}},{"code_sha256_prefix":"f04d1c1706891df6","entry":"xnli_map_hypothesis_premise","repo":"google-research/multilingual-t5","repo_kind":"official","path":"multilingual_t5/preprocessors.py","file_url":"https://github.com/google-research/multilingual-t5/blob/HEAD/multilingual_t5/preprocessors.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f04d1c1706891df6"}},{"code_sha256_prefix":"64c4f17ea92b71d7","entry":"xquad","repo":"google-research/multilingual-t5","repo_kind":"official","path":"multilingual_t5/preprocessors.py","file_url":"https://github.com/google-research/multilingual-t5/blob/HEAD/multilingual_t5/preprocessors.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64c4f17ea92b71d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}